Home / Browse

Browse AI Concepts & Ontology Classes

Explore 1929 artificial intelligence concepts, comprising 1487 evidence-curated algorithms, architectures, and model families alongside 442 classes projected from the Artificial Intelligence Ontology (AIO).

Filter concepts

Concept	Origin	Kind / Branch	Identifier	Evidence / Status
0/1 Adam (Linearized Adaptive-Freezing and Local-Step Compressed Adam) aka 0/1 Adam, Zero-One Adam… A single-stage communication-efficient distributed Adam optimization algorithm that linearizes Adam updates to support simultaneous 1-bit er…	Curated	Algorithms	`AIMech:ZeroOneAdamLinearizedLocalStepCompressedAdam`	4 claims 3 sources
1-bit Adam (Two-Stage Preconditioner-Frozen Error-Compensated Adam) aka 1-bit Adam, One-Bit Adam… A two-stage communication-compressed adaptive optimization algorithm (Tang et al. 2021, Section 4, Algorithm 1) that runs uncompressed Adam…	Curated	Algorithms	`AIMech:OneBitAdamPreconditionerFreezeCommunicationCompression`	4 claims 3 sources
1-bit LAMB (Error-Compensated LAMB-Preconditioned Large-Batch Compressed Optimization) aka 1-bit LAMB, One-Bit LAMB… A two-stage communication-efficient large-batch distributed optimization algorithm that runs uncompressed LAMB for T_w warmup steps while tr…	Curated	Algorithms	`AIMech:OneBitLambAdaptiveLayerwiseCompressedTraining`	4 claims 3 sources
3PC Three Point Compressors for Communication-Efficient Distributed Training aka 3PC, Three Point Compressors… A unified class of parameterized compression mechanisms C_{h,y}: R^d -> R^d (Three Point Compressors, 3PC) conditioned on two state vectors…	Curated	Algorithms	`AIMech:ThreePointCompressorsForCommunicationEfficientDistributedTraining`	4 claims 3 sources
5GCS (Fifth-Generation Local Training with Client Sampling) aka 5GCS, Fifth-Generation Local Training… An accelerated fifth-generation local training (LT) federated optimization framework for minimizing mu-strongly convex and L-smooth distribu…	Curated	Algorithms	`AIMech:FiveGcsFifthGenerationLocalTrainingWithClientSampling`	4 claims 3 sources
A-star beam search for sequence decoding aka A* beam search for sequence decoding A sequence-decoding beam framework that ranks active hypotheses by accumulated score plus an optimistic future-score heuristic, uses shorter…	Curated	Algorithms	`AIMech:SequenceAStarBeamSearch`	2 claims 2 sources
A-star search aka A* search A heuristic graph-search method that selects an open node using the sum of its best known path cost from the start and an estimated remainin…	Curated	Algorithms	`AIMech:AStarSearch`	1 claim 1 source
ABRA-s progressive betweenness approximation aka ABRA-s, ABRA static progressive betweenness approximation A progressive sampling algorithm for static-graph betweenness that averages fractions of shortest paths through each node over uniformly sam…	Curated	Algorithms	`AIMech:ABRASProgressiveBetweenness`	6 claims 1 source
ABRA-s-fix fixed-sample betweenness approximation aka ABRA-s-fix, ABRA fixed-sample betweenness approximation A fixed-sample static-graph betweenness algorithm that averages shortest-path fractions over a user-specified number of uniform endpoint pai…	Curated	Algorithms	`AIMech:ABRASFixedSampleBetweenness`	6 claims 1 source
Absolute threshold pruning for sequence beams A sequence-beam pruning procedure that first applies the beam-size cap, then discards candidates whose score is at least a specified positiv…	Curated	Algorithms	`AIMech:AbsoluteThresholdBeamPruning`	2 claims 2 sources
AbstractRNNCell A layer representing an RNN cell that is the base class for implementing RNN cells with custom behavior.	AIO	Layer	`AIO:AbstractRNNCell`	Imported
Acc-DNGD (Accelerated Distributed Nesterov Gradient Descent) aka Acc-DNGD, Accelerated Distributed Nesterov Gradient Descent… An accelerated decentralized first-order optimization method (Qu & Li 2020, Section II, Algorithms 1-2, Equations 3a-3d and 4a-4d) that coup…	Curated	Algorithms	`AIMech:AccDngdAcceleratedDistributedNesterovGradientDescent`	4 claims 3 sources
Accelerated Gradient and Negative-Curvature Exploitation for Non-Convex Optimization aka Carmon-Duchi-Hinder-Sidford (CDHS) Accelerated Non-Convex Method, Almost-Convex Accelerated Gradient Descent and Negative-Curvature-Descent… Accelerated Gradient and Negative-Curvature Exploitation for Non-Convex Optimization is a Hessian-free first-order and Hessian-vector-produc…	Curated	Algorithms	`AIMech:AcceleratedGradientAndNegativeCurvatureExploitationForNonConvexOptimization`	3 claims 3 sources
Accelerated graph degree linkage aka AGDL An approximate graph degree linkage algorithm that selects merges from maintained cluster-neighbor sets and updates those sets locally inste…	Curated	Algorithms	`AIMech:AcceleratedGraphDegreeLinkage`	1 claim 1 source
Accordion (Critical-Regime Adaptive Gradient Communication and Batch-Size Scheduler) aka Accordion, Accordion Adaptive Gradient Communication… An adaptive communication scheduling algorithm for synchronous data-parallel distributed training that detects critical learning regimes at…	Curated	Algorithms	`AIMech:AccordionCriticalRegimeAdaptiveGradientCommunication`	4 claims 3 sources
Accumulating Sarsa(lambda) An episodic tabular on-policy control algorithm that propagates each selected-next-action temporal-difference error through accumulating sta…	Curated	Algorithms	`AIMech:AccumulatingSarsaLambda`	6 claims 8 sources
ACProp Momentum-Centered Asynchronous Adaptive Gradient Optimization aka ACProp, ACProp Optimizer… ACProp (Asynchronous-Centering-Prop) is a first-order adaptive gradient optimization algorithm for stochastic non-convex and online convex o…	Curated	Algorithms	`AIMech:ACPropMomentumCenteringAsynchronousAdaptiveGradientOptimization`	5 claims 3 sources
Activation Layer A layer that applies an activation function to an output.	AIO	Layer	`AIO:ActivationLayer`	Imported
Activation-Value Gaussian Pooling aka Diff-Gauss pooling A parameterized neural pooling unit that averages a group of transformed activations using normalized Gaussian-kernel weights determined by…	Curated	Mathematical Methods	`AIMech:ActivationValueGaussianPooling`	5 claims 1 source
Active CMA covariance update A matrix-valued covariance-update component from the original 2006 active CMA construction that combines retained search covariance and an e…	Curated	Mathematical Methods	`AIMech:ActiveCMACovarianceUpdate`	6 claims 1 source
Active Learning aka Query Learning A machine learning task focused on methods that interactively query a user or another information source to label new data points with the d…	AIO	MachineLearningTask	`AIO:ActiveLearning`	Imported
Activity Bias A use and interpretation bias occurring when systems/platforms get training data from their most active users rather than less active or ina…	AIO	Bias	`AIO:ActivityBias`	Imported
ActivityRegularization Layer A regularization layer that applies an update to the cost function based on input activity.	AIO	Layer	`AIO:ActivityRegularizationLayer`	Imported
AD-PSGD (Asynchronous Decentralized Parallel Stochastic Gradient Descent) aka AD-PSGD, Asynchronous Decentralized Parallel Stochastic Gradient Descent… An asynchronous decentralized stochastic optimization algorithm (Lian, Zhang, Zhang, & Liu 2018, Section 3, Algorithm 1, Equation 2) for non…	Curated	Algorithms	`AIMech:AdPsgdAsynchronousDecentralizedParallelStochasticGradientDescent`	4 claims 3 sources
AdaBelief Optimizer aka AdaBelief, Adapting Stepsizes by the Belief in Observed Gradients… An adaptive first-order stochastic optimization algorithm that adapts coordinate-wise stepsizes according to the 'belief' in the observed st…	Curated	Algorithms	`AIMech:AdaBeliefStepsizeAdaptationByBeliefInObservedGradients`	4 claims 3 sources
AdaBERT (Task-Adaptive BERT Compression with Differentiable Neural Architecture Search) aka AdaBERT, Task-Adaptive BERT Compression with Differentiable Neural Architecture Search… AdaBERT is a task-adaptive BERT compression framework that uses differentiable Neural Architecture Search (NAS) to jointly optimize a macro…	Curated	Algorithms	`AIMech:AdaBERTTaskAdaptiveBERTCompressionWithDifferentiableNAS`	4 claims 3 sources
AdaBoost aka Adaptive boosting Boosting that reweights training observations according to prior prediction errors.	Curated	Algorithms	`AIMech:AdaBoost`	1 claim 1 source
AdaBound and AMSBound Dynamic Learning-Rate Bounds Optimization aka AdaBound, AMSBound… AdaBound and AMSBound are first-order adaptive stochastic optimization algorithms (Luo, Xiong, Liu, & Sun, ICLR 2019) that eliminate both ex…	Curated	Algorithms	`AIMech:AdaBoundAndAmsBoundDynamicLearningRateBoundsOptimization`	4 claims 3 sources
AdaCGD and Ada3PC Adaptive Three-Point Compression for Distributed Optimization aka Ada3PC, AdaCGD… An adaptive communication compression framework and family of distributed optimization methods introduced by Makarenko, Gasanov, Islamov, Sa…	Curated	Algorithms	`AIMech:AdaCgdAndAda3PcAdaptiveThreePointCompressionForDistributedOptimization`	4 claims 3 sources
AdaComp (Adaptive Residual Gradient Compression) aka AdaComp, Adaptive Residual Gradient Compression… An O(N) sorting-free residual gradient compression algorithm for data-parallel distributed deep learning that updates each layer's accumulat…	Curated	Algorithms	`AIMech:AdaCompAdaptiveResidualGradientCompression`	4 claims 3 sources
Adadelta An adaptive gradient optimization method that rescales gradients using exponentially weighted squared-gradient and squared-update histories.	Curated	Algorithms	`AIMech:Adadelta`	1 claim 1 source
Adafactor An adaptive gradient optimization method that approximates matrix-valued second-moment statistics using row and column factors.	Curated	Algorithms	`AIMech:Adafactor`	1 claim 2 sources
Adagrad An adaptive gradient optimization method that scales each coordinate's update using accumulated squared gradients.	Curated	Algorithms	`AIMech:Adagrad`	1 claim 1 source
AdaHessian (Adaptive Second-Order Optimizer) aka AdaHessian, AdaHessian Optimizer… An adaptive second-order stochastic optimization algorithm with O(d) memory complexity that approximates the Hessian diagonal at step t via…	Curated	Algorithms	`AIMech:AdaHessianAdaptiveSecondOrderOptimizer`	4 claims 3 sources
AdaLomo (Low-Memory Optimization with Adaptive Learning Rate) aka AdaLomo, AdaLomo Optimizer… A memory-efficient full-parameter adaptive optimization algorithm for large language models that fuses gradient backpropagation with in-plac…	Curated	Algorithms	`AIMech:AdaLomoLowMemoryAdaptiveLearningRateOptimization`	5 claims 3 sources
Adam aka Adaptive moment estimation Stochastic gradient optimization using bias-corrected exponential estimates of first and second gradient moments to scale parameter updates.	Curated	Algorithms	`AIMech:Adam`	2 claims 2 sources
Adam-mini (Hessian-Block-Partitioned Learning Rate Optimization) aka Adam-mini, Adam-mini Optimizer… A memory-efficient adaptive first-order optimization algorithm that partitions neural network parameters into blocks corresponding to the sm…	Curated	Algorithms	`AIMech:AdamMiniHessianBlockPartitionedLearningRateOptimization`	5 claims 3 sources
AdaMax An Adam-family optimizer using an exponentially weighted infinity-norm gradient scale instead of a second raw moment denominator.	Curated	Algorithms	`AIMech:AdaMax`	1 claim 1 source
AdaMixUp aka Adaptive MixUp An adaptive interpolation-training procedure that learns example-dependent mixing-coefficient regions with a policy network and trains a cla…	Curated	Algorithms	`AIMech:AdaMixUp`	2 claims 2 sources
AdamNC An Adam-family optimization method that uses time-dependent first- and second-moment decay schedules.	Curated	Algorithms	`AIMech:AdamNC`	1 claim 1 source
AdaMod aka Adaptive and Momental Bound Method for Stochastic Learning, Momental Step-Size Upper-Bounded Adaptive Optimization… An adaptive stochastic gradient optimization algorithm that restricts extreme coordinate-wise adaptive learning rates eta_t = alpha_t / (sqr…	Curated	Algorithms	`AIMech:AdaMod`	4 claims 3 sources
AdamW An Adam optimization variant that applies weight decay directly to parameters separately from gradient moment estimation.	Curated	Algorithms	`AIMech:AdamW`	1 claim 1 source
Adan (Adaptive Nesterov Momentum Algorithm) aka Adan Optimizer, Adaptive Nesterov Momentum Estimation… An adaptive first-order stochastic optimization algorithm for deep neural networks that reformulates Nesterov accelerated gradient via Neste…	Curated	Algorithms	`AIMech:AdanAdaptiveNesterovMomentumAlgorithm`	5 claims 3 sources
Adaptation sampling An online optimizer-hyperparameter controller that compares sample quality under a current and a hypothetical setting, using either fresh ev…	Curated	Algorithms	`AIMech:AdaptationSampling`	6 claims 3 sources
AdapterFusion aka AdapterFusion Non-Destructive Task Composition, Two-Stage Adapter Knowledge Extraction and Composition… A two-stage multi-task transfer learning architecture and algorithm that first extracts task-specific knowledge into N bottleneck adapters {…	Curated	Architectures	`AIMech:AdapterFusion`	4 claims 3 sources
AdaptFormer aka AdaptMLP, AdaptFormer-Swin… A parameter-efficient Vision Transformer adaptation architecture that replaces each encoder block's feed-forward network (MLP) with a dual-b…	Curated	Architectures	`AIMech:AdaptFormer`	3 claims 3 sources
Adaptive Alternating Minimization aka AAM (adaptive alternating minimization) A two-coordinate minimization procedure that performs one exact alternating sweep over a newly supplied pair of feasible sets at each iterat…	Curated	Algorithms	`AIMech:AdaptiveAlternatingMinimization`	4 claims 1 source
Adaptive data-driven optimal p-value weighting aka ADDOW (Adaptive Data-Driven Optimal Weighting), Multi-Weighted Benjamini-Hochberg Procedure (MWBH)… An adaptive grouped multiple-testing methodology (Durand 2019, Electronic Journal of Statistics 13(2):3336-3385, arXiv:1710.01094) that gene…	Curated	Mathematical Methods	`AIMech:AdaptiveDataDrivenOptimalPValueWeighting`	4 claims 3 sources
Adaptive Deconvolutional Network An unsupervised hierarchical image-representation architecture that alternates convolutional sparse synthesis with spatial and cross-map poo…	Curated	Architectures	`AIMech:AdaptiveDeconvolutionalNetwork`	5 claims 2 sources
Adaptive Lasso and Median-of-Ratios Consistent Invalid Instrument Selection in Linear Instrumental Variables Models aka Windmeijer Median-of-Ratios Adaptive Lasso Invalid IV Selection, Adaptive Lasso for Instrumental Variables with Invalid Instruments… A two-step consistent invalid-instrument selection and structural parameter estimation method (introduced by Frank Windmeijer, Helmut Farbma…	Curated	Mathematical Methods	`AIMech:AdaptiveLassoAndMedianOfRatiosConsistentInvalidInstrumentSelectionInLinearInstrumentalVariablesModels`	3 claims 2 sources
Adaptive Metropolis aka Adaptive Metropolis algorithm A history-adaptive random-walk Metropolis sampler whose Gaussian proposal covariance is estimated from the accumulated retained states, incl…	Curated	Algorithms	`AIMech:AdaptiveMetropolis`	1 claim 2 sources
Adaptive Non-Monotone Threshold Sampling for Low-Adaptivity Submodular Maximization aka ADAPTIVE-NONMONOTONE-MAX, NON-MONOTONE-THRESHOLD-SAMPLING… Adaptive Non-Monotone Threshold Sampling (ADAPTIVE-NONMONOTONE-MAX and its core subroutine NON-MONOTONE-THRESHOLD-SAMPLING) is a parallel lo…	Curated	Algorithms	`AIMech:AdaptiveNonMonotoneThresholdSamplingSubmodularMaximization`	3 claims 3 sources
Adaptive parallel tempering aka Adaptive parallel tempering algorithm A parallel-tempering algorithm that adapts temperature gaps and within-replica random-walk proposal parameters through projected stochastic…	Curated	Algorithms	`AIMech:AdaptiveParallelTempering`	1 claim 1 source
Adaptive rejection sampling aka ARS The Gilks–Wild univariate rejection sampler that uses tangents to a concave log density as a piecewise-linear upper hull and chords as a low…	Curated	Algorithms	`AIMech:AdaptiveRejectionSampling`	1 claim 1 source
Adaptive scaling Metropolis aka ASM A random-walk Metropolis algorithm that adapts its proposal scale through stochastic approximation driven by the proposal acceptance probabi…	Curated	Algorithms	`AIMech:AdaptiveScalingMetropolis`	1 claim 1 source
Adaptive scaling within adaptive Metropolis aka ASWAM An adaptive Metropolis algorithm that combines acceptance-rate-driven scalar proposal scaling with recursive mean and covariance-shape adapt…	Curated	Algorithms	`AIMech:AdaptiveScalingWithinAdaptiveMetropolis`	1 claim 1 source
AdaptiveAvgPool1D Layer aka AdaptiveAvgPool1D A pooling layer that applies a 1D adaptive average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AdaptiveAvgPool1DLayer`	Imported
AdaptiveAvgPool2D Layer aka AdaptiveAvgPool2D A pooling layer that applies a 2D adaptive average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AdaptiveAvgPool2DLayer`	Imported
AdaptiveAvgPool3D Layer aka AdaptiveAvgPool3D A pooling layer that applies a 3D adaptive average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AdaptiveAvgPool3DLayer`	Imported
AdaptiveMaxPool1D Layer aka AdaptiveMaxPool1D A pooling layer that applies a 1D adaptive max pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AdaptiveMaxPool1DLayer`	Imported
AdaptiveMaxPool2D Layer aka AdaptiveMaxPool2D A pooling layer that applies a 2D adaptive max pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AdaptiveMaxPool2DLayer`	Imported
AdaptiveMaxPool3D Layer aka AdaptiveMaxPool3D A pooling layer that applies a 3D adaptive max pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AdaptiveMaxPool3DLayer`	Imported
AdaShift aka Adaptive Learning Rate Method with Temporal Shifting, Temporally Shifted Second-Moment Decorrelated Adam… An adaptive learning rate optimization algorithm that eliminates the positive correlation between the second-moment scale v_t and the curren…	Curated	Algorithms	`AIMech:AdaShift`	4 claims 3 sources
AdaSum Adaptive Summation for Distributed Training aka AdaSum, Adaptive Summation for Distributed Training… A hyperparameter-free distributed gradient and model-update reduction operator that replaces naive all-reduce summation across data-parallel…	Curated	Algorithms	`AIMech:AdaSumAdaptiveSummationForDistributedTraining`	4 claims 3 sources
Add Layer A merging layer that adds a list of inputs taking as input a list of tensors all of the same shape.	AIO	Layer	`AIO:AddLayer`	Imported
Addition Layer A layer that adds inputs from one or more other layers to cells or neurons of a target layer.	AIO	Layer	`AIO:AdditionLayer`	Imported
AdditiveAttention Layer An attention layer that implements additive attention also known as Bahdanau-style attention.	AIO	Layer	`AIO:AdditiveAttentionLayer`	Imported
AdEMAMix (Adaptive EMA Mixture Optimizer) aka AdEMAMix Optimizer, Adaptive Exponential Moving Average Mixture Optimizer… An AdamW-based adaptive optimization algorithm (Algorithm 1) that replaces the single first-moment exponential moving average with a linear…	Curated	Algorithms	`AIMech:AdEMAMixAdaptiveEMAMixtureOptimization`	3 claims 3 sources
AdGD (Adaptive Gradient Descent without Descent) aka AdGD Optimizer, Adaptive Gradient Descent without Line Search… A line-search-free, function-value-free adaptive gradient descent algorithm (Algorithm 1) that updates iterates via x^{k+1} = x^k - lambda_k…	Curated	Algorithms	`AIMech:AdGDAdaptiveGradientDescentWithoutDescent`	4 claims 3 sources
ADIANA Accelerated Distributed Nesterov Gradient Descent with Compression aka ADIANA, ACGD… An accelerated distributed optimization algorithm with unbiased communication compression (ADIANA, together with its single-node counterpart…	Curated	Algorithms	`AIMech:AdianaAcceleratedDistributedNesterovGradientDescentWithCompression`	4 claims 3 sources
Admixture of Poisson Markov random fields aka Admixture of Poisson MRFs, APM A probabilistic topic-model family that draws each document from a proper Poisson-MRF base distribution whose canonical unary and interactio…	Curated	Model Families	`AIMech:AdmixtureOfPoissonMarkovRandomFields`	2 claims 6 sources
ADOPT (Adaptive Gradient Descent with Optimal Convergence) aka ADOPT Optimizer, Modified Adam with Optimal Convergence for Any Beta2… An adaptive first-order stochastic optimization algorithm that modifies Adam in two structural ways so that it converges to first-order stat…	Curated	Algorithms	`AIMech:AdoptModifiedAdamOptimalConvergenceAnyBeta2`	5 claims 3 sources
ADORE and STAR Hard-Negative Dense Retrieval Training Framework aka ADORE, STAR and ADORE… A two-stage hard-negative training algorithm and theoretical optimization framework for bi-encoder dense retrieval that first trains both qu…	Curated	Algorithms	`AIMech:ADOREOptimizingDenseRetrievalModelTrainingWithHardNegatives`	4 claims 3 sources
Adversarial debiasing (Zhang et al.) aka Zhang projected-gradient adversarial debiasing An adversarial learning algorithm that trains a task predictor alongside a protected-attribute adversary, modifying the predictor gradient w…	Curated	Algorithms	`AIMech:ZhangAdversarialDebiasing`	2 claims 2 sources
Affine-Invariant Calibrated Covariance Estimation and Heavy-Tailed Ridge Regression aka Calibrated Heavy-Tailed Covariance Estimation via Dyadic Regularization Halving (Ostrovskii & Rudi 2019), Affine-Invariant Iterative Norm-Truncated Covariance Estimator… Affine-Invariant Calibrated Covariance Estimation and Heavy-Tailed Ridge Regression is a non-asymptotic statistical estimation and regressio…	Curated	Mathematical Methods	`AIMech:AffineInvariantCalibratedCovarianceEstimationAndHeavyTailedRidgeRegression`	4 claims 3 sources
Age-Granularity-Net Multi-Granularity Classification-Regression Framework aka Age-Granularity-Net, Multi-Granularity Classification-Regression Network… A multi-head neural network training architecture for continuous/ordinal visual estimation that attaches multiple parallel classification br…	Curated	Architectures	`AIMech:AgeGranularityNetMultiGranularityClassificationRegressionFramework`	4 claims 3 sources
Aggregated Momentum (AggMo Passive Damping Optimizer) aka AggMo, Aggregated Momentum Optimizer… A multi-velocity first-order momentum optimization method inspired by passive structural damping that maintains K parallel velocity vectors…	Curated	Algorithms	`AIMech:AggMoAggregatedMomentumPassiveDampingOptimization`	5 claims 3 sources
Agnostic Federated Learning via Minimax Distributionally Robust Optimization aka Agnostic Federated Learning, AFL… A distributionally robust federated learning framework and stochastic minimax optimization algorithm (Agnostic Federated Learning, AFL) that…	Curated	Algorithms	`AIMech:AgnosticFederatedLearningMinimaxDistributionallyRobustOptimization`	4 claims 3 sources
Alecton Riemannian-Rescaled Stochastic Gradient Descent for Non-Convex Low-Rank Matrix Problems aka Alecton Algorithm, Alecton Non-Convex Low-Rank Factorized SGD… Alecton is a two-phase stochastic gradient descent algorithm introduced by De Sa, Olukotun, and Re (2015) for solving non-convex low-rank fa…	Curated	Algorithms	`AIMech:AlectonStochasticGradientDescentForNonconvexLowRankMatrixProblems`	3 claims 3 sources
Alpha-Skew Random Walk Fourth-Moment Tightness and Tauberian Return Convolution aka Seol Fourth-Order Moment Tightness Proof for Alpha-Skew Random Walks, Alpha-Skew Random Walk Tauberian Return Convolution Formulation A stochastic-process convergence and fourth-order moment tightness formulation for the linearly interpolated rescaled alpha-skew random walk…	Curated	Mathematical Methods	`AIMech:AlphaSkewRandomWalkFourthMomentTightnessAndTauberianReturnConvolution`	4 claims 3 sources
AlphaDropout Layer A regularization layer that applies Alpha Dropout to the input keeping mean and variance of inputs to ensure self-normalizing property.	AIO	Layer	`AIO:AlphaDropoutLayer`	Imported
Alternating Expectation Conditional Maximization aka AECM, AECM Algorithm A likelihood-optimization framework that alternates cycles of expectation and constrained maximization, permitting the admissible data augme…	Curated	Algorithms	`AIMech:AlternatingExpectationConditionalMaximization`	4 claims 1 source
Alternating Kullback-Leibler Minimization aka Alternating I-Divergence Minimization, Alternating Information Projection A paired-distribution optimization procedure that alternately minimizes Kullback-Leibler divergence in its first and second arguments over s…	Curated	Algorithms	`AIMech:AlternatingKullbackLeiblerMinimization`	4 claims 1 source
AltMinPhase and SparseAltMinPhase (Resampled Alternating Minimization for Phase Retrieval) aka AltMinPhase (Alternating Minimization for Phase Retrieval), SparseAltMinPhase (Sparse Phase Retrieval via Alternating Minimization and CoSaMP)… The first non-convex alternating minimization algorithm with provable global geometric convergence for phase retrieval and sparse phase retr…	Curated	Algorithms	`AIMech:AltMinPhaseAndSparseAltMinPhaseAlternatingMinimizationPhaseRetrieval`	4 claims 3 sources
AltMinSense and AltMinComplete (Alternating Minimization for Low-Rank Matrix Sensing and Completion) aka AltMinSense and AltMinComplete, Jain-Netrapalli-Sanghavi Alternating Minimization for Matrix Sensing and Completion… The first globally provable alternating least-squares algorithms — AltMinSense for rank-$k$ matrix sensing $\mathcal{A}(M) = b$ and *AltMi…	Curated	Algorithms	`AIMech:AltMinSenseAndAltMinCompleteAlternatingMinimizationForLowRankMatrixSensingAndCompletion`	4 claims 3 sources
AMC (AutoML for Model Compression and Acceleration on Mobile Devices) aka AMC, AutoML for Model Compression… AMC (AutoML for Model Compression) is a reinforcement-learning-based neural network pruning framework that processes a pretrained network la…	Curated	Algorithms	`AIMech:AMCAccelerationAndModelCompressionOnMobileDevicesWithRL`	4 claims 3 sources
AMIS Adaptive Multiple Importance Sampling with Past-Weight Recycling aka Adaptive Multiple Importance Sampling, AMIS Past-Weight Recycling Importance Sampler… An adaptive importance sampling algorithm that iteratively updates parametric proposal distributions (such as multivariate Student-t densiti…	Curated	Algorithms	`AIMech:AMISAdaptiveMultipleImportanceSamplingWithPastWeightRecycling`	4 claims 3 sources
Amortized Stein variational gradient descent aka Amortized SVGD A differentiable stochastic-sampler training procedure that repeatedly generates a minibatch, computes kernelized Stein target-score directi…	Curated	Algorithms	`AIMech:AmortizedSteinVariationalGradientDescent`	6 claims 2 sources
Amortized-Filtering and Iterative-Filtering for Optimal Logarithmic-Adaptivity Submodular Maximization aka Balkanski-Rubinstein-Singer Amortized-Filtering Algorithm, Iterative-Filtering and Amortized-Filtering for Low-Adaptivity Submodular Maximization… Amortized-Filtering and Iterative-Filtering for Optimal Logarithmic-Adaptivity Submodular Maximization is a parallel value-oracle algorithmi…	Curated	Algorithms	`AIMech:AmortizedFilteringForLogarithmicAdaptivitySubmodularMaximization`	3 claims 3 sources
Amplification Bias A processing bias arising when the distribution over prediction outputs is skewed compared to the prior distribution of the prediction targe…	AIO	Bias	`AIO:AmplificationBias`	Imported
AMSGrad An Adam variant that normalizes first-moment updates with the coordinatewise historical maximum of second-moment estimates.	Curated	Algorithms	`AIMech:AMSGrad`	1 claim 1 source
Analog Lagrange Coded Computing for Privacy-Preserving Floating-Point Distributed Computation aka Analog Lagrange Coded Computing, ALCC… An analog coded distributed computing algorithm that extends Lagrange Coded Computing from finite fields to real and complex floating-point…	Curated	Algorithms	`AIMech:AnalogLagrangeCodedComputingForPrivacyPreservingFloatingPointDistributedComputation`	4 claims 3 sources
Analytic moment-based Gaussian-process filtering aka Gaussian-process assumed-density filtering, GP-ADF A Gaussian assumed-density filtering algorithm that uses trained squared-exponential Gaussian-process transition and measurement models, ana…	Curated	Algorithms	`AIMech:AnalyticMomentBasedGaussianProcessFiltering`	5 claims 2 sources
ANCE Approximate Nearest Neighbor Negative Contrastive Learning aka ANCE, Approximate Nearest Neighbor Negative Contrastive Estimation… A contrastive representation learning algorithm for dense text retrieval that resolves the diminishing gradient norms and high stochastic gr…	Curated	Algorithms	`AIMech:ANCEApproximateNearestNeighborNegativeContrastiveLearning`	4 claims 3 sources
Ancestral Gumbel-Top-k sampling An exact without-replacement sampler for finite discrete Bayesian-network configurations that propagates conditional Gumbel subtree maxima t…	Curated	Algorithms	`AIMech:AncestralGumbelTopKSampling`	3 claims 1 source
Anchor Words and RecoverL2 Topic-Word Matrix Factorization aka FastAnchorWords and RecoverL2 Topic Modeling, Anchor-Word Provable Topic Modeling Algorithm… Anchor Words and RecoverL2 Topic-Word Matrix Factorization is a practical polynomial-time provable topic modeling pipeline introduced by Aro…	Curated	Algorithms	`AIMech:AnchorWordsAndRecoverL2TopicWordMatrixFactorization`	3 claims 3 sources
Anchoring Bias An individual bias characterized by the influence of a reference point or anchor on decisions leading to insufficient adjustment from that a…	AIO	Bias	`AIO:AnchoringBias`	Imported
AND/OR abstraction sampling aka Unrestricted AND/OR abstraction sampling An importance-sampling algorithm for partition functions of discrete graphical models that samples representatives in a pseudo-tree-guided A…	Curated	Algorithms	`AIMech:ANDORAbstractionSampling`	5 claims 2 sources
ANITA Optimal Loopless Accelerated Variance-Reduced Gradient Method aka ANITA, AN optImal loopless acceleraTed vAriance-reduced gradient method… A loopless (single-loop) accelerated variance-reduced gradient method introduced by Li (2021) for solving general convex (mu = 0) and mu-str…	Curated	Algorithms	`AIMech:AnitaOptimalLooplessAcceleratedVarianceReducedGradientMethod`	4 claims 3 sources
Annealed importance sampling aka AIS A Monte Carlo estimation algorithm that draws from a tractable base distribution, applies Markov transitions invariant for a prescribed sequ…	Curated	Algorithms	`AIMech:AnnealedImportanceSampling`	6 claims 1 source
Annotator Reporting Bias An individual bias occurring when users rely on automation as a heuristic replacement for their own information seeking and processing.	AIO	Bias	`AIO:AnnotatorReportingBias`	Imported
Ant colony optimization aka ACO, Ant colony optimization metaheuristic A metaheuristic framework for optimization in which artificial ants construct solutions using local information and communicate indirectly t…	Curated	Algorithms	`AIMech:AntColonyOptimization`	1 claim 1 source
Ant Colony System aka ACS An ant-colony optimization algorithm that combines a greedy-or-proportional construction rule, local pheromone updates during construction,…	Curated	Algorithms	`AIMech:AntColonySystem`	1 claim 2 sources
Ant System A constructive combinatorial optimization method in which artificial ants sample solution components using shared pheromone trails and probl…	Curated	Algorithms	`AIMech:AntSystem`	1 claim 1 source
Ant-based telephone routing A distributed telephone-routing algorithm that adapts neighbor-choice probabilities using mobile ant agents. Ants sample moves from destinat…	Curated	Algorithms	`AIMech:AntBasedTelephoneRouting`	5 claims 1 source
Ant-Q A family of cooperative ant-based optimization algorithms that learns shared edge desirabilities using Q-learning-inspired next-state estima…	Curated	Algorithms	`AIMech:AntQ`	1 claim 2 sources
AntNet A distributed adaptive routing algorithm in which forward agents sample network paths and backward agents use the measured trip times to upd…	Curated	Algorithms	`AIMech:AntNet`	1 claim 1 source
APFL (Adaptive Personalized Federated Learning via Convex Global-Local Model Interpolation) aka APFL, Adaptive Personalized Federated Learning… A personalized federated optimization algorithm and generalization framework (Deng, Kamani, & Mahdavi 2020, Sections 2-4, Equations 2-10, Th…	Curated	Algorithms	`AIMech:ApflAdaptivePersonalizedFederatedLearningViaConvexGlobalLocalModelInterpolation`	4 claims 3 sources
Apollo (Adaptive Parameter-wise Diagonal Quasi-Newton Optimizer) aka Apollo Optimizer, ApolloW… A diagonal quasi-Newton algorithm for nonconvex stochastic optimization that approximates the Hessian diagonally for each decoupled paramete…	Curated	Algorithms	`AIMech:ApolloAdaptiveParameterWiseDiagonalQuasiNewtonOptimization`	5 claims 3 sources
Apriori Frequent-itemset mining using breadth-first candidate enumeration and support-based pruning.	Curated	Algorithms	`AIMech:Apriori`	1 claim 1 source
AR2 Adversarial Retriever-Ranker for Dense Text Retrieval aka AR2, Adversarial Retriever-Ranker… A joint adversarial training algorithm for dense text retrieval that couples a dual-encoder retriever G_theta(q, d) = E_theta(q)^T E_theta(d…	Curated	Algorithms	`AIMech:AR2AdversarialRetrieverRankerForDenseTextRetrieval`	4 claims 3 sources
Archimedean copula linear step-up false discovery rate bounds and calibration aka Bodnar-Dickhaus Archimedean Copula Linear Step-Up FDR Bound Framework, Archimedean p-Value Copula Benjamini-Hochberg FDR Upper and Lower Bounds… A statistical multiple hypothesis testing and False Discovery Rate (FDR) analysis framework developed by Taras Bodnar and Thorsten Dickhaus…	Curated	Mathematical Methods	`AIMech:ArchimedeanCopulaStepUpFDRBounds`	4 claims 4 sources
Artificial Neural Network aka ANN, NN A network based on a collection of connected units called artificial neurons modeled after biological neurons.	AIO	Network	`AIO:ArtificialNeuralNetwork`	Imported
Association Rule Learning A supervised learning focused on a rule-based approach for discovering interesting relations between variables in large databases.	AIO	MachineLearningTask	`AIO:AssociationRuleLearning`	Imported
Asymmetric Low-Rank Matrix Eigenvalue and Linear-Form Eigenvector Perturbation Analysis aka Asymmetrically Perturbed Low-Rank Eigen-Decomposition, Chen-Cheng-Fan Asymmetric Matrix Perturbation Theory… A non-asymptotic spectral perturbation theory (established by Yuxin Chen, Chen Cheng, and Jianqing Fan in 2021) for estimating the leading e…	Curated	Mathematical Methods	`AIMech:AsymmetricLowRankEigenvalueAndLinearFormEigenvectorPerturbationAnalysis`	3 claims 3 sources
asymptotically optimal rejection curve false discovery rate control and adjusted step-up-down testing aka Finner-Dickhaus-Roters Asymptotically Optimal Rejection Curve (AORC) Framework, Dirac-Uniform Asymptotically Optimal Rejection Curve f_alpha(t) = t / (t*(1 - alpha) + alpha)… An asymptotic and finite-sample multiple hypothesis testing framework introduced by Helmut Finner, Thorsten Dickhaus, and Markus Roters (200…	Curated	Mathematical Methods	`AIMech:AsymptoticallyOptimalRejectionCurveFDRControl`	4 claims 3 sources
Asynchronous Successive Halving aka ASHA, Asynchronous Successive Halving Algorithm An asynchronous resource-allocation algorithm that promotes promising completed hyperparameter trials through increasing resource levels as…	Curated	Algorithms	`AIMech:AsynchronousSuccessiveHalving`	1 claim 2 sources
Atomic Norm Convex Geometry and Tangent Cone Gaussian Width for Linear Inverse Problems aka Atomic Norm Minimization and Tangent Cone Gaussian Width, Chandrasekaran-Recht-Parrilo-Willsky Atomic Norm Framework… Atomic Norm Convex Geometry and Tangent Cone Gaussian Width for Linear Inverse Problems is a unified convex-geometric framework for recoveri…	Curated	Mathematical Methods	`AIMech:AtomicNormConvexGeometryAndTangentConeGaussianWidthForLinearInverseProblems`	3 claims 3 sources
ATOMO (Atomic Sparsification for Communication-Efficient Distributed Learning) aka ATOMO, Atomic Sparsification for Distributed Learning… A general unbiased gradient sparsification framework (Wang et al. 2018, Section 3, Algorithm 1) that expresses a gradient tensor g in R^d in…	Curated	Algorithms	`AIMech:AtomoAtomicSparsificationForDistributedLearning`	4 claims 3 sources
ATTEMPT (Attentional Mixtures of Prompt Tuning) aka ATTEMPT, ATTEMPT-m… A modular parameter-efficient multi-task language model tuning method that pre-trains reusable soft source prompts on high-resource tasks an…	Curated	Algorithms	`AIMech:ATTEMPTAttentionalMixturesOfSoftPrompts`	4 claims 3 sources
Attention Layer A layer that implements dot-product attention also known as Luong-style attention.	AIO	Layer	`AIO:AttentionLayer`	Imported
Attention-Based Configurable Convolutional Neural Network aka ABC-CNN A visual-question-answering architecture that derives a convolution kernel from an encoded question to compute normalized spatial attention,…	Curated	Architectures	`AIMech:AttentionBasedConfigurableConvolutionalNeuralNetwork`	6 claims 1 source
Attention-Based Convolutional Neural Network aka ABCNN A sentence-pair neural architecture that uses cross-sentence distance affinities to add attention feature channels before convolution, rewei…	Curated	Architectures	`AIMech:AttentionBasedConvolutionalNeuralNetwork`	6 claims 1 source
Attention-based Dropout Layer aka ADL A training-time convolutional feature-map layer that stochastically applies either a thresholded spatial drop mask or sigmoid importance wei…	Curated	Layers & Modules	`AIMech:AttentionBasedDropoutLayer`	1 claim 1 source
Attentive Pooling Network aka Attentive Pooling Networks A neural sentence-pair architecture that learns bilinear segment interactions, derives attention by row and column maxima followed by separa…	Curated	Architectures	`AIMech:AttentivePoolingNetwork`	6 claims 1 source
Author-persona-topic model aka APT A probabilistic topic-model family in which each author has a mixture of personas, each persona has a topic distribution, and one persona sh…	Curated	Model Families	`AIMech:AuthorPersonaTopicModel`	3 claims 1 source
Author-recipient-topic model aka ART A generative message model with a topic distribution for each ordered sender-recipient pair, in which each word selects a recipient uniforml…	Curated	Model Families	`AIMech:AuthorRecipientTopicModel`	2 claims 2 sources
Author-topic model A generative document model in which each author has a shared topic-proportion distribution and each word is produced by uniformly selecting…	Curated	Model Families	`AIMech:AuthorTopicModel`	2 claims 1 source
Auto Encoder Network aka AE An unsupervised pretrained network that learns efficient codings of unlabeled data by training to ignore insignificant data and regenerate i…	AIO	Network	`AIO:AutoEncoderNetwork`	Imported
Auto-binomial Markov random field aka Auto-binomial model, Auto-binomial scheme A finite pairwise Markov-field model for bounded site counts whose full conditionals are binomial with fixed trial counts and log odds linea…	Curated	Model Families	`AIMech:AutoBinomialMarkovRandomField`	1 claim 1 source
Auto-exponential Markov random field aka Auto-exponential model, Auto-exponential scheme A finite pairwise Markov-field model for nonnegative continuous site values with exponential full conditionals whose rates are positive base…	Curated	Model Families	`AIMech:AutoExponentialMarkovRandomField`	1 claim 1 source
Auto-normal Markov random field aka Auto-normal model, Auto-normal scheme… A proper finite Gaussian Markov-field model specified by linear full-conditional means and positive, value-independent site conditional vari…	Curated	Model Families	`AIMech:AutoNormalMarkovRandomField`	1 claim 2 sources
Auto-Poisson Markov random field aka Auto-Poisson model, Auto-Poisson scheme A finite pairwise Markov-field model for unbounded nonnegative integer counts whose full conditionals are Poisson with log means linear in n…	Curated	Model Families	`AIMech:AutoPoissonMarkovRandomField`	1 claim 1 source
Auto-Walksat A preprocessing-and-run algorithm that estimates a fixed noise setting for a stochastic SAT solver by probing a terminal-score mean-to-stand…	Curated	Algorithms	`AIMech:AutoWalksat`	5 claims 2 sources
AutoAugment An automated augmentation-policy search procedure that trains a controller to propose image-transform subpolicies and rewards those proposal…	Curated	Algorithms	`AIMech:AutoAugment`	1 claim 1 source
Automation Complacency Bias aka Automation Complaceny An individual bias characterized by over-reliance on automated systems leading to attenuated human skills.	AIO	Bias	`AIO:AutomationComplacencyBias`	Imported
AutoPrompt Gradient-Guided Discrete Prompt Search aka AutoPrompt, AutoPrompt Gradient-Guided Prompt Generation… An automated discrete prompt construction and knowledge-probing algorithm for pretrained language models that maps task inputs x_inp into a…	Curated	Algorithms	`AIMech:AutoPromptGradientGuidedDiscretePromptSearch`	4 claims 3 sources
Autoregressive Conditional Heteroskedasticity aka ARCH A model that describes the variance of the current error term as a function of the previous periods' error terms, capturing volatility clust…	AIO	Model	`AIO:AutoregressiveConditionalHeteroskedasticity`	Imported
Autoregressive conditional restricted Boltzmann machine aka Autoregressive CRBM A neural sequence architecture that models each current vector with a conditional RBM whose visible and hidden biases are affine functions o…	Curated	Architectures	`AIMech:AutoregressiveConditionalRestrictedBoltzmannMachine`	1 claim 2 sources
Autoregressive Distributed Lag aka ARDL A model that includes lagged values of both the dependent variable and one or more independent variables, capturing dynamic relationships ov…	AIO	Model	`AIO:AutoregressiveDistributedLag`	Imported
Autoregressive Integrated Moving Average aka ARIMA A model which combines autoregression (AR), differencing (I), and moving average (MA) components. Used for analyzing and forecasting time se…	AIO	Model	`AIO:AutoregressiveIntegratedMovingAverage`	Imported
Autoregressive Language Model aka generative language model, sequence-to-sequence model A language model that generates text sequentially predicting one token at a time based on the previously generated tokens excelling at natur…	AIO	Model	`AIO:AutoregressiveLanguageModel`	Imported
Autoregressive Moving Average aka ARMA A model that combines autoregressive (AR) and moving average (MA) components to represent time series data, suitable for stationary series w…	AIO	Model	`AIO:AutoregressiveMovingAverage`	Imported
Availability Heuristic Bias aka Availability Bias, Availability Heuristic An individual bias characterized by a mental shortcut where easily recalled information is overweighted in judgment and decision-making.	AIO	Bias	`AIO:AvailabilityHeuristicBias`	Imported
Average Layer A merging layer that averages a list of inputs element-wise taking as input a list of tensors all of the same shape.	AIO	Layer	`AIO:AverageLayer`	Imported
Averaged stochastic gradient descent aka ASGD A stochastic gradient optimization method that maintains an average of parameter iterates in addition to the current iterate.	Curated	Algorithms	`AIMech:AveragedStochasticGradientDescent`	1 claim 1 source
AveragePooling1D Layer aka AvgPool1D A pooling layer that performs average pooling for temporal data.	AIO	Layer	`AIO:AveragePooling1DLayer`	Imported
AveragePooling2D Layer aka AvgPool2D A pooling layer that performs average pooling for spatial data.	AIO	Layer	`AIO:AveragePooling2DLayer`	Imported
AveragePooling3D Layer aka AvgPool3D A pooling layer that performs average pooling for 3D data (spatial or spatio-temporal).	AIO	Layer	`AIO:AveragePooling3DLayer`	Imported
AvgPool1D Layer aka AvgPool1D A pooling layer that applies a 1D average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AvgPool1DLayer`	Imported
AvgPool2D Layer aka AvgPool2D A pooling layer that applies a 2D average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AvgPool2DLayer`	Imported
AvgPool3D Layer aka AvgPool3D A pooling layer that applies a 3D average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:AvgPool3DLayer`	Imported
Away-Step and Pairwise Frank-Wolfe Linear Convergence on Polytopes aka Lacoste-Julien and Jaggi Global Linear Convergence of Frank-Wolfe Variants, Away-Steps Frank-Wolfe (AFW) and Pairwise Frank-Wolfe (PFW)… Away-Step and Pairwise Frank-Wolfe Linear Convergence on Polytopes is a projection-free conditional gradient framework and affine-invariant…	Curated	Algorithms	`AIMech:AwayStepAndPairwiseFrankWolfeLinearConvergenceOnPolytopes`	3 claims 3 sources
B-PROP Bootstrapped Pre-Training with Representative Words Prediction for Ad-Hoc Retrieval aka B-PROP, Bootstrapped Pre-training with Representative Words Prediction… A bootstrapped self-supervised pre-training algorithm for ad-hoc document retrieval that extracts final-layer head-averaged [CLS]-token self…	Curated	Algorithms	`AIMech:BPROPBootstrappedPreTrainingWithRepresentativeWordsPrediction`	4 claims 3 sources
Backfed Input Layer An input layer that receives values from another layer.	AIO	Layer	`AIO:BackfedInputLayer`	Imported
Backpropagation through time aka BPTT A reverse differentiation algorithm that computes derivatives of a finite dynamic-system objective by propagating adjoints backward through…	Curated	Algorithms	`AIMech:BackpropagationThroughTime`	6 claims 1 source
BAdam (Block Coordinate Descent with Adam's Update Rule) aka BAdam, BAdam Optimizer… A memory-efficient full-parameter optimization algorithm for large language models that partitions model parameters theta in R^d into D orde…	Curated	Algorithms	`AIMech:BAdamBlockCoordinateAdamFullParameterOptimization`	4 claims 3 sources
Bagging aka Bootstrap aggregating Ensemble learning that aggregates predictors trained on bootstrap samples.	Curated	Algorithms	`AIMech:Bagging`	1 claim 1 source
Baik-Ben Arous-Peche Largest Eigenvalue Phase Transition for Spiked Complex Sample Covariance Matrices aka BBP Phase Transition for Spiked Sample Covariance Matrices, Baik-Ben Arous-Peche Spiked Wishart Largest Eigenvalue Limit Laws… Baik-Ben Arous-Peche Largest Eigenvalue Phase Transition for Spiked Complex Sample Covariance Matrices is a random-matrix spectral fluctuati…	Curated	Mathematical Methods	`AIMech:BaikBenArousPecheLargestEigenvaluePhaseTransition`	3 claims 3 sources
Baik-Silverstein Eigenvalue Separation for High-Dimensional Spiked Population Covariance Matrices aka Baik-Silverstein Spiked Population Covariance Eigenvalue Limit Theorem, Non-Gaussian Spiked Sample Covariance Outlier Eigenvalue Separation… Baik-Silverstein Eigenvalue Separation for High-Dimensional Spiked Population Covariance Matrices is a random-matrix spectral analysis metho…	Curated	Mathematical Methods	`AIMech:BaikSilversteinSpikedPopulationCovarianceEigenvalueSeparation`	2 claims 3 sources
Balanced Attention Mechanism aka BAM (balanced attention) A convolutional feature-gating component for single-image super-resolution that computes average-pooled channel attention and maximum-pooled…	Curated	Layers & Modules	`AIMech:BalancedAttentionMechanism`	6 claims 1 source
Balanced largest differencing method aka BLDM, Balanced LDM A two-way number-partitioning heuristic that first differences disjoint adjacent pairs in the sorted original list, then repeatedly differen…	Curated	Algorithms	`AIMech:BalancedLargestDifferencing`	6 claims 1 source
Ball vector machine aka BVM An approximate SVM training procedure that uses fixed-radius enclosing-ball center updates in a transformed kernel feature space, with multi…	Curated	Algorithms	`AIMech:BallVectorMachine`	7 claims 2 sources
Barber–Agakov mutual information bound aka Barber-Agakov bound, BA bound A variational lower bound on mutual information formed by adding input entropy to the expected log probability assigned by a normalized cond…	Curated	Mathematical Methods	`AIMech:BarberAgakovBound`	1 claim 2 sources
Barker acceptance rule An acceptance-probability rule for reversible Monte Carlo proposals that uses R/(1+R), where R is the target-density ratio times the reverse…	Curated	Mathematical Methods	`AIMech:BarkerAcceptanceRule`	1 claim 1 source
Barlow Twins A self-supervised representation-learning procedure that trains shared encoder and projection networks to make the cross-correlation of two…	Curated	Algorithms	`AIMech:BarlowTwins`	1 claim 3 sources
BASGD Buffered Asynchronous Stochastic Gradient Descent for Byzantine Learning aka BASGD, Buffered Asynchronous SGD… An asynchronous Byzantine-resilient parameter-server optimization algorithm proposed by Yang and Li (ICML 2021) that resists malicious worke…	Curated	Algorithms	`AIMech:BasgdBufferedAsynchronousStochasticGradientDescentForByzantineLearning`	4 claims 3 sources
BasicILS aka BasicILS(N) A ParamILS algorithm-configuration method that compares candidate configurations using cost estimates on the same fixed number of target-alg…	Curated	Algorithms	`AIMech:BasicILS`	1 claim 1 source
Basis Learn (BL1, BL2, and BL3) aka Basis Learn, BL1 Basis Learn with Bidirectional Compression… A family of communication-efficient second-order distributed and federated optimization algorithms (BL1, BL2, and BL3) for minimizing f(x) =…	Curated	Algorithms	`AIMech:BasisLearnCustomMatrixBasisSecondOrderFederatedOptimization`	4 claims 3 sources
Basis pursuit A signal-representation optimization principle that minimizes the L1 norm of real synthesis coefficients subject to exact reconstruction of…	Curated	Mathematical Methods	`AIMech:BasisPursuit`	7 claims 1 source
Batch reciprocal-nearest-neighbor agglomeration aka Reciprocal-neighbor batch clustering, de Rham reciprocal-neighbor clustering An agglomerative clustering procedure that alternates finding reciprocal nearest-neighbor pairs across the current clusters with merging a b…	Curated	Algorithms	`AIMech:BatchReciprocalNearestNeighborClustering`	6 claims 3 sources
BatchNorm1D Layer aka BatchNorm1D A batch normalization layer that applies Batch Normalization over a 2D or 3D input.	AIO	Layer	`AIO:BatchNorm1DLayer`	Imported
BatchNorm2D Layer aka BatchNorm2D A batch normalization layer that applies Batch Normalization over a 4D input.	AIO	Layer	`AIO:BatchNorm2DLayer`	Imported
BatchNorm3D Layer aka BatchNorm3D A batch normalization layer that applies Batch Normalization over a 5D input.	AIO	Layer	`AIO:BatchNorm3DLayer`	Imported
BatchNormalization Layer aka BatchNorm A normalization layer that normalizes its inputs applying a transformation that maintains the mean close to 0 and the standard deviation clo…	AIO	Layer	`AIO:BatchNormalizationLayer`	Imported
Bayes optimal p-value weighting under a Gaussian prior on the effect sizes aka Bayes P-Value Weights, Gaussian-Prior Optimal P-Value Weighting… A frequentist multiple hypothesis testing p-value weighting methodology (and informed genome-wide association study procedure, iGWAS) introd…	Curated	Mathematical Methods	`AIMech:BayesOptimalPValueWeightingUnderGaussianPrior`	4 claims 3 sources
Bayesian Data Augmentation for Deep Models aka Bayesian Data Augmentation, Bayesian DA… Tran et al.’s supervised deep-learning procedure that treats synthetic labeled examples as latent data, repeatedly samples them from an evol…	Curated	Algorithms	`AIMech:BayesianDataAugmentation`	1 claim 1 source
Bayesian Network A network that is a probabilistic graphical model representing variables and their conditional dependencies via a directed acyclic graph.	AIO	Network	`AIO:BayesianNetwork`	Imported
Beam decoding with a monotone-score stopping certificate aka Optimal-ending beam search A layer-based sequence beam decoder that retains the best completed hypothesis seen so far and stops when the highest current prefix score c…	Curated	Algorithms	`AIMech:OptimalStoppingBeamDecoding`	2 claims 2 sources
Beam search using limited discrepancy backtracking aka BULB, Limited discrepancy beam search A memory-bounded beam search that explores heuristic-ranked slices using increasing limited-discrepancy budgets and removes backtracked slic…	Curated	Algorithms	`AIMech:BULB`	3 claims 3 sources
Beam-stack search A layer-based beam search augmented with a stack of admitted evaluation ranges so that backtracking systematically revisits successors previ…	Curated	Algorithms	`AIMech:BeamStackSearch`	2 claims 2 sources
BEER Gradient Tracking with Communication Compression for Decentralized Nonconvex Optimization aka BEER, BEER Decentralized Compressed Gradient Tracking… A communication-compressed decentralized nonconvex optimization algorithm (BEER) that couples EF21-style Markov contractive error-feedback s…	Curated	Algorithms	`AIMech:BeerGradientTrackingWithCommunicationCompressionForDecentralizedNonconvexOptimization`	4 claims 3 sources
Behavioral Bias An individual bias characterized by systematic distortions in user behavior across platforms or contexts or across users represented in diff…	AIO	Bias	`AIO:BehavioralBias`	Imported
Berrut Approximated Coded Computing for Straggler-Resilient Non-Polynomial Distributed Computation aka Berrut Approximated Coded Computing, BACC… A numerically stable straggler-resilient coded computing scheme over the real numbers R for approximately evaluating arbitrary (possibly non…	Curated	Algorithms	`AIMech:BerrutApproximatedCodedComputingForStragglerResilientNonPolynomialDistributedComputation`	3 claims 3 sources
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing aka BERT-of-Theseus, Theseus Compression for BERT… A distillation-loss-free Transformer compression algorithm ('Theseus Compression') that partitions a frozen N-layer predecessor network P =…	Curated	Algorithms	`AIMech:BERToftheseusCompressingBERTByProgressiveModuleReplacing`	4 claims 3 sources
BERT-PKD (Patient Knowledge Distillation for BERT Model Compression) aka BERT-PKD, Patient Knowledge Distillation… A multi-layer knowledge distillation method for compressing a deep pre-trained BERT teacher into a shallower n-layer BERT_n student (Sun, Ch…	Curated	Learning Paradigms	`AIMech:BERTPKDPatientKnowledgeDistillationForBERTModelCompression`	3 claims 3 sources
Best-first beam search with a global frontier cap A best-first search procedure that limits the entire open frontier to a fixed number of nodes by discarding the worst-ranked frontier nodes…	Curated	Algorithms	`AIMech:GlobalFrontierBeamSearch`	3 claims 3 sources
Best-first beam search with per-length budgets The sequence-decoding beam procedure of Meister, Vieira and Cotterell that prioritizes active hypotheses by decreasing accumulated score, br…	Curated	Algorithms	`AIMech:SequenceBestFirstBeamSearch`	3 claims 3 sources
Best-first search A search strategy that repeatedly expands the open node with the best value under a specified evaluation rule, adding eligible successors to…	Curated	Algorithms	`AIMech:BestFirstSearch`	2 claims 2 sources
Betting confidence sequences for bounded random variables aka Hedged Capital Process Confidence Sequence (Hedged-CS), Predictable Plug-in Empirical Bernstein Confidence Sequence (PrPl-EB)… A nonparametric, nonasymptotic sequential and fixed-sample statistical inference framework (Waudby-Smith & Ramdas 2024) for estimating the c…	Curated	Mathematical Methods	`AIMech:BettingConfidenceSequencesForBoundedMeans`	4 claims 3 sources
BI-population CMA-ES The original 2009 multistart CMA-ES algorithm that interlaces increasing-population attempts with randomized smaller population and initial-…	Curated	Algorithms	`AIMech:BIPOPCMAES`	6 claims 2 sources
Bias A systematic error introduced into sampling or testing by selecting or encouraging one outcome or answer over others.	AIO	Bias	`AIO:Bias`	Imported
Biclustering aka Block Clustering, Co-clustering… A machine learning task focused on methods that simultaneously cluster the rows and columns of a matrix to identify submatrices with coheren…	AIO	MachineLearningTask	`AIO:Biclustering`	Imported
Bidirectional Layer A recurrent layer that is a bidirectional wrapper for RNNs.	AIO	Layer	`AIO:BidirectionalLayer`	Imported
Bidirectional Transformer Language Model aka BERT, Bidirectional Transformer LM A transformer language model such as BERT that uses the transformer architecture to build deep bidirectional representations by predicting m…	AIO	Model	`AIO:BidirectionalTransformerLanguageModel`	Imported
Binary Classification A classification focused on methods that classify elements into two groups based on a classification rule.	AIO	MachineLearningTask	`AIO:BinaryClassification`	Imported
Binary Multiple Kernel Maximum Margin Clustering aka Two-Class Multiple Kernel Clustering A two-class unsupervised clustering procedure that jointly fits a nonnegative multiple-kernel combination and absolute-margin classifier usi…	Curated	Algorithms	`AIMech:BinaryMultipleKernelMaximumMarginClustering`	5 claims 1 source
BIRCH aka Balanced Iterative Reducing and Clustering using Hierarchies Clustering that compresses observations into a clustering-feature tree for subsequent grouping.	Curated	Algorithms	`AIMech:BIRCH`	1 claim 1 source
Bivariate counterfactual-fairness sensitivity analysis aka Kilbertus grid-based counterfactual-fairness sensitivity A model-based sensitivity procedure that varies the correlation between two structural error terms and measures how a predictor built under…	Curated	Evaluation Methods	`AIMech:BivariateCounterfactualFairnessSensitivity`	1 claim 1 source
Black box variational inference aka BBVI A variational-inference procedure that estimates evidence-lower-bound gradients from samples of a tractable variational distribution using i…	Curated	Algorithms	`AIMech:BlackBoxVariationalInference`	1 claim 2 sources
Black-Box Tuning (BBT) for Language-Model-as-a-Service aka Black-Box Tuning, BBT… A derivative-free continuous prompt optimization method for Language-Model-as-a-Service (LMaaS) inference APIs that exploits the low intrins…	Curated	Algorithms	`AIMech:BBTBlackBoxTuningForLanguageModelAsAService`	4 claims 3 sources
Blahut-Arimoto Rate-Distortion Algorithm aka Blahut Rate-Distortion Algorithm An alternating channel-and-marginal minimization algorithm for a fixed-source rate-distortion problem at a specified nonnegative distortion…	Curated	Algorithms	`AIMech:BlahutArimotoRateDistortionAlgorithm`	4 claims 2 sources
Block-matching and 3D filtering aka BM3D A grayscale image-denoising algorithm that stacks similar square patches into three-dimensional groups, jointly shrinks their transform coef…	Curated	Algorithms	`AIMech:BlockMatching3DFiltering`	6 claims 1 source
BOHB aka Bayesian Optimization and Hyperband A hyperparameter optimization algorithm combining Hyperband resource brackets with model-guided configuration proposals from performance-spl…	Curated	Algorithms	`AIMech:BOHB`	2 claims 4 sources
Boltzmann chain A family of tied-weight undirected Boltzmann sequence models with hidden temporal variables, observed variables and chain-derived connectivi…	Curated	Model Families	`AIMech:BoltzmannChain`	2 claims 2 sources
Boltzmann Machine Network aka BM, Sherrington–Kirkpatrick model with external field… A symmetrically connected network that is a type of stochastic recurrent neural network and Markov random field.	AIO	Network	`AIO:BoltzmannMachineNetwork`	Imported
Boosting Ensemble learning that sequentially adds learners to improve an existing predictor.	Curated	Learning Paradigms	`AIMech:Boosting`	1 claim 1 source
Bootstrap classifier-instability novelty detection aka Outlier detection using classifier instability, Bootstrap output-variance novelty detection A novelty-detection procedure that trains classifiers on bootstrap resamples of reference data, estimates the variance of their outputs at a…	Curated	Algorithms	`AIMech:BootstrapClassifierInstabilityNoveltyDetection`	4 claims 1 source
Bootstrap Your Own Latent aka BYOL A self-supervised image representation-learning procedure that trains an online predictor to match a stopped-gradient target projection from…	Curated	Algorithms	`AIMech:BootstrapYourOwnLatent`	1 claim 2 sources
Bottleneck Attention Module aka BAM (bottleneck attention) A convolutional feature refinement component that combines parallel channel and spatial attention branches and adds the resulting gated feat…	Curated	Layers & Modules	`AIMech:BottleneckAttentionModule`	2 claims 2 sources
Bounded adaptive reward for sequence scoring A beam-dependent sequence rescoring rule that adds per-step rewards derived from the beam’s mean negative log token probability, accumulatin…	Curated	Mathematical Methods	`AIMech:BoundedAdaptiveReward`	1 claim 1 source
Bounded length reward for sequence scoring aka Bounded word reward A sequence scoring rule that adds a fixed nonnegative reward per generated position up to a finite length cap, giving score S(y)+r·min(l,\|y\|…	Curated	Mathematical Methods	`AIMech:BoundedLengthReward`	2 claims 2 sources
Bounded word reward with predicted length A sequence rescoring method that adds a fixed word reward only up to an input-specific length predicted from encoder states, replacing a cor…	Curated	Mathematical Methods	`AIMech:PredictedLengthBoundedReward`	1 claim 1 source
Brandes betweenness centrality computation aka Brandes algorithm An exact graph algorithm for computing shortest-path vertex betweenness that combines single-source shortest-path counting with reverse-dist…	Curated	Algorithms	`AIMech:BrandesBetweennessCentrality`	7 claims 1 source
Brandes–Fleischer current-flow betweenness computation aka Brandes-Fleischer exact current-flow betweenness An exact network-analysis algorithm that computes current-flow betweenness by forming grounded-Laplacian current-response rows, sorting each…	Curated	Algorithms	`AIMech:BrandesFleischerCurrentFlowBetweenness`	6 claims 1 source
Brandes–Fleischer grounded current-flow closeness computation aka Brandes-Fleischer grounded resistance-sum closeness algorithm An exact network-analysis algorithm that accumulates effective-resistance sums from successive columns of an embedded grounded-Laplacian inv…	Curated	Algorithms	`AIMech:BrandesFleischerGroundedCurrentFlowCloseness`	6 claims 1 source
Brandes–Fleischer sampled-pair current-flow betweenness aka Brandes-Fleischer current-flow betweenness approximation A randomized network-analysis algorithm that estimates normalized, endpoint-excluded current-flow betweenness by independently sampling unif…	Curated	Algorithms	`AIMech:BrandesFleischerSampledCurrentFlowBetweenness`	6 claims 1 source
Brandes–Pich pivot-based centrality estimation aka Brandes-Pich centrality estimation A network-analysis procedure that estimates shortest-path closeness and betweenness from single-source computations at a selected subset of…	Curated	Algorithms	`AIMech:BrandesPichPivotCentralityEstimation`	7 claims 1 source
Breadth-first beam search aka Beam search A heuristic search procedure that advances by depth layers, retaining at most a chosen beam width of the best-ranked candidate nodes for eac…	Curated	Algorithms	`AIMech:BeamSearch`	2 claims 2 sources
Breadth-first branch-and-bound search aka BFBnB A heuristic graph-search procedure that expands states in breadth-first layers and prunes candidate paths whose accumulated cost plus an adm…	Curated	Algorithms	`AIMech:BreadthFirstBranchAndBound`	2 claims 2 sources
Breadth-first iterative-deepening A-star aka BFIDA, Breadth-first iterative-deepening A An iterative-deepening heuristic graph-search algorithm that repeatedly runs breadth-first branch-and-bound within increasing hypothetical f…	Curated	Algorithms	`AIMech:BreadthFirstIDAStar`	2 claims 2 sources
Breadth-first search aka BFS, Breadth first traversal A graph or state-space traversal that expands vertices in nondecreasing shortest-path distance from a start vertex, where distance counts ed…	Curated	Algorithms	`AIMech:BreadthFirstSearch`	2 claims 2 sources
Breakout method aka Breakout A finite constraint-satisfaction search method that takes strictly improving local assignment changes under a weighted nogood cost and incre…	Curated	Algorithms	`AIMech:BreakoutMethod`	1 claim 1 source
Brevity-penalty normalization for sequence scoring aka BP-Norm A sequence rescoring rule that adds a predicted-length brevity penalty in log space to average token log probability: S(x,y)/\|y\| + min(1−Lpr…	Curated	Mathematical Methods	`AIMech:BrevityPenaltyNormalization`	2 claims 2 sources
BRIDGE Byzantine-Resilient Decentralized Gradient Descent aka BRIDGE, BRIDGE-T… A Byzantine-resilient decentralized empirical risk minimization framework over a directed network G(J, E) of M nodes with up to b Byzantine…	Curated	Algorithms	`AIMech:BridgeByzantineResilientDecentralizedGradientDescent`	3 claims 3 sources
Bucketing Resampling for Heterogeneous Byzantine-Robust Optimization aka s-Bucketing for Byzantine-Robust Learning, Bucketing Agnostic Robust Aggregator… A randomized pre-aggregation resampling reduction (s-Bucketing, Algorithm 1) for Byzantine-robust distributed optimization on heterogeneous…	Curated	Algorithms	`AIMech:BucketingResamplingForHeterogeneousByzantineRobustOptimization`	4 claims 3 sources
Bulyan (Byzantine-Resilient Gradient Meta-Aggregation Rule) aka Bulyan, Bulyan Gradient Aggregation… Bulyan (or Bulyan(A)) is a two-stage Byzantine-resilient gradient meta-aggregation rule for distributed stochastic gradient descent over n >…	Curated	Algorithms	`AIMech:BulyanByzantineResilientGradientAggregation`	3 claims 3 sources
Burer-Monteiro Low-Rank Semidefinite Programming and Riemannian Staircase aka Smooth Burer-Monteiro Riemannian SDP Factorization, Boumal-Voroninski-Bandeira Benign Non-Convexity above the Barvinok-Pataki Bound… Burer-Monteiro Low-Rank Semidefinite Programming and Riemannian Staircase is a non-convex Riemannian optimization framework analyzed by Boum…	Curated	Mathematical Methods	`AIMech:BurerMonteiroLowRankSemidefiniteProgrammingAndRiemannianStaircase`	3 claims 3 sources
Byrd-SAGA Byzantine-Resilient Distributed SAGA with Geometric Median Aggregation aka Byrd-SAGA, Byzantine Attack Resilient Distributed SAGA… A Byzantine-resilient federated finite-sum optimization algorithm for minimizing f(x) = (1 / (W - B)) sum_{w notin B} (1 / J) sum_{j=1}^J f_…	Curated	Algorithms	`AIMech:ByrdSagaByzantineResilientDistributedSagaWithGeometricMedianAggregation`	3 claims 3 sources
ByRDiE Byzantine-Resilient Distributed Coordinate Descent for Decentralized Learning aka ByRDiE, Byzantine-Resilient Distributed Coordinate Descent… A Byzantine-resilient decentralized optimization algorithm (ByRDiE) that decomposes a P-dimensional empirical risk minimization problem acro…	Curated	Algorithms	`AIMech:ByrdieByzantineResilientDistributedCoordinateDescentForDecentralizedLearning`	4 claims 3 sources
Byzantine-Robust Stochastic Aggregation for Heterogeneous Datasets aka RSA, l1-RSA… A family of Byzantine-robust distributed stochastic learning methods for heterogeneous (non-i.i.d.) worker datasets that reformulates distri…	Curated	Algorithms	`AIMech:RsaByzantineRobustStochasticAggregationForHeterogeneousDatasets`	3 claims 3 sources
C4.5 Decision-tree induction extending ID3 with tests on continuous-valued features.	Curated	Algorithms	`AIMech:C45`	1 claim 1 source
Calibrate Before Use Contextual Calibration aka Calibrate Before Use, Contextual Calibration… A data-free output-probability calibration method for zero-shot and few-shot in-context language models that counteracts majority label bias…	Curated	Algorithms	`AIMech:CalibrateBeforeUseContextualCalibration`	4 claims 3 sources
CAME (Confidence-guided Adaptive Memory Efficient Optimization) aka CAME Optimizer, Confidence-guided Adaptive Memory-Efficient Optimizer… A memory-efficient adaptive optimization algorithm (Algorithm 2) that extends Adafactor by computing the elementwise squared residual instab…	Curated	Algorithms	`AIMech:CAMEConfidenceGuidedAdaptiveMemoryEfficientOptimization`	3 claims 3 sources
CANITA Compressed Accelerated Gradient Method for Distributed Convex Optimization aka CANITA, Compressed Accelerated Gradient Method CANITA… A compressed Nesterov-style accelerated gradient algorithm for distributed smooth convex optimization across n machines (Algorithm 1) that c…	Curated	Algorithms	`AIMech:CanitaCompressedAcceleratedGradientMethodForDistributedConvexOptimization`	4 claims 3 sources
CART aka Classification and Regression Trees Decision-tree induction using binary recursive partitioning for classification or regression.	Curated	Algorithms	`AIMech:CART`	1 claim 1 source
Catalyst Universal Acceleration for First-Order Optimization aka Lin-Mairal-Harchaoui Catalyst Generic Acceleration Scheme, Inexact Accelerated Proximal Point Envelope for Finite-Sum Optimization… Catalyst Universal Acceleration for First-Order Optimization is a generic outer-loop inexact accelerated proximal point framework introduced…	Curated	Algorithms	`AIMech:CatalystUniversalAccelerationForFirstOrderOptimization`	3 claims 3 sources
Categorical Features Preprocessing Layer A layer that performs categorical data preprocessing operations.	AIO	Layer	`AIO:CategoricalFeaturesPreprocessingLayer`	Imported
CategoryEncoding Layer A categorical features preprocessing layer that encodes integer features providing options for condensing data into a categorical encoding.	AIO	Layer	`AIO:CategoryEncodingLayer`	Imported
Catoni-style heavy-tailed confidence sequences aka Catoni Supermartingale Confidence Sequence for Heavy-Tailed Means, Infinite-Variance p-Catoni Confidence Sequence… A family of nonasymptotic, anytime-valid sequential confidence sequences (Wang & Ramdas 2023, building on Catoni 2012) for the conditional m…	Curated	Mathematical Methods	`AIMech:CatoniStyleHeavyTailedConfidenceSequences`	4 claims 3 sources
Causal Graphical Model aka Casaul Bayesian Network, Casaul Graph… A probabilistic graphical model used to encode assumptions about the data-generating process.	AIO	MachineLearningTask	`AIO:CausalGraphicalModel`	Imported
Causal LLM aka Causal Large Language Model, autoregressive… A large language model that only attends to previous tokens in the sequence when generating text modeling the probability distribution autor…	AIO	Model	`AIO:CausalLLM`	Imported
Cautious Optimizers (C-AdamW / C-Lion Alignment-Masked Momentum) aka Cautious Optimizer, C-AdamW and C-Lion… A general element-wise sign-alignment modification for momentum-based optimization algorithms (Algorithms 1-3) that replaces a base optimize…	Curated	Algorithms	`AIMech:CautiousOptimizersAlignmentMaskedMomentumOptimization`	4 claims 3 sources
CCVR (Classifier Calibration with Virtual Representations for Federated Learning) aka CCVR, Classifier Calibration with Virtual Representations… A post-training server-side classifier calibration algorithm for non-IID federated learning (Luo et al. 2021, Section 4, Algorithm 1, Equati…	Curated	Algorithms	`AIMech:CcvrClassifierCalibrationWithVirtualRepresentationsForFederatedLearning`	4 claims 3 sources
CD-PercLoss A conditional RBM training algorithm that contrasts the observed output free energy with that of a prediction selected by input-initialized…	Curated	Algorithms	`AIMech:CDPercLoss`	1 claim 1 source
CEDR Contextualized Embeddings for Document Ranking aka CEDR, Contextualized Embeddings for Document Ranking… A joint neural document ranking architecture that replaces the single 2D static-word-embedding similarity matrix in interaction-focused neur…	Curated	Architectures	`AIMech:CEDRContextualizedEmbeddingsForDocumentRanking`	4 claims 3 sources
CEIL Compositional Exemplars for In-Context Learning aka CEIL, Compositional Exemplars for In-Context Learning… A subset-level exemplar selection algorithm for in-context learning that models the joint probability of an entire demonstration subset cond…	Curated	Algorithms	`AIMech:CEILCompositionalExemplarsForInContextLearning`	4 claims 3 sources
CenterCrop Layer An image preprocessing layer that crops the central portion of images to a target size.	AIO	Layer	`AIO:CenterCropLayer`	Imported
Centered Clipping and Worker Momentum for Byzantine-Robust Optimization aka Centered Clipping (CC), Byzantine-Robust Worker Momentum with Centered Clipping… A stateful Byzantine-robust distributed optimization framework combining: (1) local Worker Momentum m_{t,i} = (1 - alpha_t) m_{t-1,i} + alph…	Curated	Algorithms	`AIMech:CenteredClippingAndWorkerMomentumForByzantineRobustOptimization`	4 claims 3 sources
CFL (Clustered Federated Learning via Cosine Similarity Bipartitioning) aka CFL, Clustered Federated Learning via Cosine Similarity Bipartitioning… A recursive model-agnostic clustered federated learning algorithm (Sattler, Müller, & Samek 2021, Algorithm 1 & Algorithm 2) that detects cl…	Curated	Algorithms	`AIMech:CflClusteredFederatedLearningViaCosineSimilarityBipartitioning`	4 claims 3 sources
Chain of LoRA aka Chain of LoRA (COLA), COLA Iterative Residual Low-Rank Adaptation… An iterative parameter-efficient fine-tuning framework that approximates a higher-rank weight update by training a sequence of low-rank LoRA…	Curated	Algorithms	`AIMech:ChainOfLoRA`	4 claims 3 sources
Chakrabarti classifier-guided focused crawling aka Chakrabarti focused crawler, Taxonomy-guided focused crawling A focused web-acquisition procedure that uses a trained classifier over a supplied topic taxonomy to decide or prioritize hyperlink expansio…	Curated	Algorithms	`AIMech:ChakrabartiFocusedCrawler`	6 claims 1 source
Chambolle-Pock First-Order Primal-Dual Algorithm for Convex Saddle-Point Problems aka Chambolle-Pock Primal-Dual Hybrid Gradient (PDHG) Algorithm, Extrapolated Primal-Dual Proximal Splitting Algorithm… Chambolle-Pock First-Order Primal-Dual Algorithm for Convex Saddle-Point Problems is a matrix-inversion-free proximal splitting framework in…	Curated	Algorithms	`AIMech:ChambollePockFirstOrderPrimalDualAlgorithmForConvexSaddlePointProblems`	3 claims 3 sources
CHAMELEON clustering aka CHAMELEON hierarchical clustering A graph-clustering procedure that first partitions a sparse neighbor graph into small subclusters and then agglomerates them using interconn…	Curated	Algorithms	`AIMech:CHAMELEONClustering`	1 claim 1 source
Child-Tuning Gradient-Masked Subnetwork Fine-Tuning aka Child-Tuning, Child-Tuning_F and Child-Tuning_D… A fine-tuning algorithm for large-scale pretrained language models that executes the forward pass across the entire pretrained network while…	Curated	Algorithms	`AIMech:ChildTuningGradientMaskSubnetworkFineTuning`	4 claims 3 sources
Choco-SGD and Choco-Gossip Decentralized Optimization with Compressed Communication aka Choco-SGD, Choco-Gossip… A family of decentralized gossip and stochastic optimization algorithms (Choco-Gossip and Choco-SGD) over a connected network with symmetric…	Curated	Algorithms	`AIMech:ChocoSgdAndChocoGossipDecentralizedCompressedOptimization`	4 claims 3 sources
Circular weight-shift sampler A finite-state Markov transition construction that partitions a circle into intervals with target-weight lengths and derives each transition…	Curated	Algorithms	`AIMech:CircularWeightShiftSampler`	6 claims 4 sources
CLARANS clustering aka CLARANS, Clustering Large Applications based on RANdomized Search A randomized medoid-clustering algorithm that searches fixed-size sets of representative observations by accepting improving single swaps an…	Curated	Algorithms	`AIMech:CLARANSClustering`	2 claims 1 source
Classification A supervised learning focused on methods that distinguish and distribute kinds of "things" into different groups.	AIO	MachineLearningTask	`AIO:Classification`	Imported
Classification Annealing Expectation Maximization aka Classification Annealing EM, CAEM A stochastic hard-clustering algorithm that samples component assignments from current mixture posterior probabilities raised to an inverse…	Curated	Algorithms	`AIMech:ClassificationAnnealingExpectationMaximization`	3 claims 1 source
Classification Expectation Maximization aka Classification EM, CEM (classification expectation maximization) A model-based hard-clustering algorithm that computes mixture responsibilities, assigns every observation to a highest-responsibility compon…	Curated	Algorithms	`AIMech:ClassificationExpectationMaximization`	4 claims 1 source
Clauset–Newman–Moore community detection aka CNM, CNM community detection… A greedy community-detection algorithm that agglomerates graph vertices using modularity changes, with sparse change tables and heap-based m…	Curated	Algorithms	`AIMech:CNMCommunityDetection`	7 claims 2 sources
Cleaning aka Data Cleansing, Standardization… A data preparation that removes noise inconsistencies and irrelevant information from data to enhance its quality and prepare it for analysi…	AIO	Preprocessing	`AIO:Cleaning`	Imported
CLEAR Complementing Lexical Retrieval with Semantic Residual Embedding aka CLEAR, Complementing Lexical Retrieval with Semantic Residual Embedding… A hybrid lexical-semantic retrieval method that explicitly trains a dense Transformer dual-encoder embedding model to capture the semantic r…	Curated	Algorithms	`AIMech:CLEARComplementingLexicalRetrievalWithSemanticResidualEmbedding`	4 claims 3 sources
ClippedGossip Self-Centered Clipping for Byzantine-Robust Decentralized Learning aka ClippedGossip, Self-Centered Clipping… A Byzantine-robust decentralized consensus and stochastic optimization algorithm on an arbitrary communication graph G = (V, E) with regular…	Curated	Algorithms	`AIMech:ClippedGossipSelfCenteredClippingForByzantineRobustDecentralizedLearning`	3 claims 3 sources
Clique extracted ontology aka CliXO An overlapping hierarchical clustering heuristic that constructs a directed acyclic hierarchy from pairwise dissimilarities by selecting inf…	Curated	Algorithms	`AIMech:CliXO`	7 claims 1 source
Clockwork recurrent neural network aka CW-RNN, Clockwork RNN A recurrent architecture partitioning hidden units into modules with prescribed update periods, copying inactive module states and restricti…	Curated	Architectures	`AIMech:ClockworkRecurrentNeuralNetwork`	6 claims 1 source
Clustering aka Cluster analysis A machine learning task focused on methods that group a set of objects such that objects in the same group are more similar to each other th…	AIO	MachineLearningTask	`AIO:Clustering`	Imported
Clustering Data by Melting aka Melting Algorithm for Clustering A scale-dependent clustering procedure that heats Gaussian-weighted center iterations to build a merging membership tree, then selects clust…	Curated	Algorithms	`AIMech:ClusteringDataByMelting`	4 claims 1 source
CMA rank-mu covariance update A covariance-valued update component introduced in the 2003 CMA-ES construction that forms an equal-weight second moment of selected mutatio…	Curated	Mathematical Methods	`AIMech:CMARankMuCovarianceUpdate`	6 claims 1 source
COCO-DR Contrastive and Distributionally Robust Zero-Shot Dense Retrieval aka COCO-DR, COntinuous COntrastive and Implicit Distributionally Robust Dense Retrieval… A two-stage zero-shot dense retrieval training algorithm that mitigates document-side and query-side distribution shifts between a labeled s…	Curated	Algorithms	`AIMech:COCODRDenseRetrievalDistributionallyRobustContrastiveLearning`	4 claims 3 sources
coCondenser Unsupervised Corpus-Aware Language Model Pre-Training aka coCondenser, Corpus-Aware Condenser Pre-Training… A two-stage unsupervised language model pre-training algorithm for dense passage retrieval that warm-starts from a universal Condenser model…	Curated	Algorithms	`AIMech:CoCondenserUnsupervisedCorpusAwareLanguageModelPreTraining`	4 claims 3 sources
CodedPrivateML Lagrange-Coded Stochastic Quantization for Distributed Training aka CodedPrivateML, Coded Privacy-Preserving Machine Learning… A privacy-preserving distributed gradient-descent training protocol (CodedPrivateML) that deterministically quantizes a training dataset X i…	Curated	Algorithms	`AIMech:CodedPrivateMlLagrangeCodedStochasticQuantizationForDistributedTraining`	4 claims 3 sources
Cognitive Bias An individual bias characterized by deviations from rational judgment and decision-making including adaptive mental shortcuts known as heuri…	AIO	Bias	`AIO:CognitiveBias`	Imported
COIL Contextualized Inverted List aka COIL, Contextualized Inverted List… A contextualized exact lexical match retrieval architecture and inverted-list index structure that encodes document tokens offline with a pr…	Curated	Architectures	`AIMech:COILContextualizedInvertedList`	4 claims 3 sources
Communication Neural Network aka CommNet, Communication Neural Net… A neural architecture for cooperative multi-agent tasks that alternates shared per-agent hidden-state updates with continuous communication…	Curated	Architectures	`AIMech:CommunicationNeuralNetwork`	6 claims 1 source
Compacter (Low-Rank Hypercomplex Adapter Layers) aka Compacter, Compacter++… Compacter (Compact Adapter) is a parameter-efficient fine-tuning method for pretrained Transformer models that replaces the dense down-proje…	Curated	Algorithms	`AIMech:CompacterLowRankHypercomplexAdapterLayers`	3 claims 3 sources
Competitive learning An unsupervised learning paradigm in which units or modules compete to represent presented input patterns and adapt their representations ac…	Curated	Learning Paradigms	`AIMech:CompetitiveLearning`	5 claims 2 sources
Complete balanced largest differencing aka Complete BLDM A complete anytime two-way number-partitioning search that carries signed effective cardinalities through difference and sum branches, uses…	Curated	Algorithms	`AIMech:CompleteBalancedLargestDifferencing`	6 claims 1 source
Complete Dictionary Recovery Over the Sphere and Riemannian Trust-Region Method aka Complete Dictionary Recovery Over the Sphere (Sun-Qu-Wright 2017), Log-Cosh Spherical Sparsity Minimization and Riemannian Trust-Region Method… A nonconvex spherical optimization formulation and second-order Riemannian Trust-Region (RTR) algorithm over the unit sphere $\mathbb{S}^{…	Curated	Algorithms	`AIMech:CompleteDictionaryRecoveryOverTheSphereAndRiemannianTrustRegionMethod`	4 claims 3 sources
Complete greedy number partitioning aka CGA, Complete greedy algorithm for number partitioning A complete anytime number-partitioning search that assigns weights in decreasing order to a fixed number of bins, explores the currently lig…	Curated	Algorithms	`AIMech:CompleteGreedyNumberPartitioning`	6 claims 1 source
Complete Karmarkar–Karp aka CKK A complete anytime algorithm for two-way number partitioning that first follows Karmarkar–Karp differencing, then explores complementary sum…	Curated	Algorithms	`AIMech:CompleteKarmarkarKarp`	6 claims 1 source
Complete layer-wise adaptive rate scaling aka CLARS A layer-wise gradient optimization method whose published rate formula divides the current parameter-block L2 norm by the average L2 norm of…	Curated	Algorithms	`AIMech:CompleteLayerWiseAdaptiveRateScaling`	7 claims 3 sources
Complete multiway Karmarkar–Karp aka Multiway CKK A complete anytime multiway number-partitioning search that combines partial bin assignments in alternative relative permutations, explores…	Curated	Algorithms	`AIMech:CompleteMultiwayKarmarkarKarp`	6 claims 1 source
Composite HMM-topic model A generative sequence model combining an HMM class sequence with a document topic mixture, where one designated class emits words through la…	Curated	Model Families	`AIMech:CompositeHMMTopicModel`	2 claims 1 source
Compositional Generalization LLM aka Compositional Generalization Large Language Model, out-of-distribution generalization… A large language model that is trained to understand and recombine the underlying compositional structures in language enabling better gener…	AIO	Model	`AIO:CompositionalGeneralizationLLM`	Imported
Compositional spatial transformer A learnable image-alignment module that retains an original source image and accumulated warp state, samples that source under the current w…	Curated	Layers & Modules	`AIMech:CompositionalSpatialTransformer`	5 claims 1 source
CompressedScaffnew aka CompressedScaffnew Algorithm, Doubly Accelerated Scaffnew with Permutation Mask Compression A doubly accelerated distributed and federated optimization algorithm for minimizing f(x) = (1/n) sum_{i=1}^n f_i(x) across n heterogeneous…	Curated	Algorithms	`AIMech:CompressedScaffnewDoublyAcceleratedLocalTrainingAndCompression`	4 claims 3 sources
Computational Bias aka Statistical Bias A bias caused by differences between results and facts in the process of data analysis (including the source of data the estimator chose) an…	AIO	Bias	`AIO:ComputationalBias`	Imported
Concatenate Layer A merging layer that concatenates a list of inputs taking as input a list of tensors all of the same shape except for the concatenation axis…	AIO	Layer	`AIO:ConcatenateLayer`	Imported
Concept Drift Bias aka Concept Drift A use and interpretation bias due to the use of a system outside its planned domain of application causing performance gaps between laborato…	AIO	Bias	`AIO:ConceptDriftBias`	Imported
Concurrent planning and execution metareasoning model A formal metareasoning model that represents competing plan-computation processes, their known executable action heads and induced-deadline…	Curated	Model Families	`AIMech:ConcurrentPlanningExecutionModel`	6 claims 2 sources
Condensed nearest-neighbor data domain description aka CNNDD, Condensed NNDD rule A greedy reference-selection algorithm for the NNDD distance-norm decision rule that uses two passes over the original observations followed…	Curated	Algorithms	`AIMech:CondensedNearestNeighborDataDomainDescription`	5 claims 1 source
Condensed prototype-based domain description aka CPDD, Greedy prototype domain condensation A greedy prototype-selection procedure that constructs kth-neighbor radius offsets from the full reference dataset and repeatedly chooses th…	Curated	Algorithms	`AIMech:CondensedPrototypeBasedDomainDescription`	4 claims 1 source
Condenser (Pre-Training Architecture for Dense Retrieval) aka Condenser Transformer Pre-Training Architecture, CONdition on DENSE Representation Architecture… A transformer pre-training architecture for dense bi-encoder representation learning that partitions the encoder backbone into L^e early lay…	Curated	Architectures	`AIMech:CondenserPreTrainingArchitectureForDenseRetrieval`	3 claims 3 sources
Conditional calibration for false discovery rate control under dependence aka Dependency-Adjusted Benjamini-Hochberg Procedure, dBH Procedure… A finite-sample multiple-testing methodology (Fithian & Lei 2022, The Annals of Statistics 50(6):3091-3118, arXiv:2007.10438) that controls…	Curated	Mathematical Methods	`AIMech:ConditionalCalibrationForFalseDiscoveryRateControl`	4 claims 3 sources
Conditional Distribution Prediction for IDA* aka Conditional Distribution Prediction A search-effort estimation procedure that predicts the number of expanded nodes in a complete IDA* threshold iteration by recursively propag…	Curated	Algorithms	`AIMech:ConditionalDistributionPredictionIDAStar`	5 claims 1 source
Conditional restricted Boltzmann machine aka CRBM, Conditional RBM A conditional neural probability model that represents an output vector with an RBM whose biases or interactions are determined by a supplie…	Curated	Architectures	`AIMech:ConditionalRestrictedBoltzmannMachine`	1 claim 1 source
Cone Invertibility Factor Oracle Inequalities and Rate Minimaxity of LASSO and Dantzig Selector in Lq Loss aka Cone Invertibility Factor (CIF) and Sign-Restricted CIF (SCIF), Ye-Zhang Cone Invertibility Factor and Lq Minimax Oracle Inequalities… A sharp non-asymptotic Gram-matrix invertibility and minimax estimation framework (introduced by Fei Ye and Cun-Hui Zhang in 2010) that unif…	Curated	Mathematical Methods	`AIMech:ConeInvertibilityFactorOracleInequalitiesAndRateMinimaxityOfLassoAndDantzigSelectorInLqLoss`	3 claims 2 sources
Confirmation Bias An individual bias characterized by the tendency to prefer information that confirms existing beliefs influencing the search for interpretat…	AIO	Bias	`AIO:ConfirmationBias`	Imported
Conformer-Kernel with Query Term Independence for Document Retrieval aka Conformer-Kernel with Query Term Independence, Conformer-Kernel… An efficient neural document retrieval and ranking architecture (Mitra, Hofstätter, Zamani, & Craswell, 2020) that modifies the Transformer-…	Curated	Architectures	`AIMech:ConformerKernelWithQueryTermIndependenceForDocumentRetrieval`	4 claims 3 sources
Conic Statistical Dimension, Intrinsic Volume Concentration, and Approximate Kinematic Phase Transitions in Random Convex Programs aka Amelunxen-Lotz-McCoy-Tropp Conic Statistical Dimension and Phase Transitions, Statistical Dimension of Convex Cones and Approximate Conic Kinematic Formula… Conic Statistical Dimension, Intrinsic Volume Concentration, and Approximate Kinematic Phase Transitions in Random Convex Programs is a coni…	Curated	Mathematical Methods	`AIMech:ConicStatisticalDimensionIntrinsicVolumeConcentrationAndPhaseTransitions`	3 claims 3 sources
Conjugate-gradient Monte Carlo aka CGMC A population Markov sampler that obtains a local-optimization anchor from one population member and updates another member along the anchor…	Curated	Algorithms	`AIMech:ConjugateGradientMonteCarlo`	1 claim 1 source
Consistency model aka Consistency models, CM (consistency model) A generative model family that learns a noise- or time-conditioned function mapping points on a probability-flow ODE trajectory to its commo…	Curated	Model Families	`AIMech:ConsistencyModel`	2 claims 2 sources
Constrained convex p-value weighting in monotone likelihood ratio families (Princessp) aka Princessp, Prior-Informed Convexly Constrained Spjotvoll P-Value Weighting… A convex-optimization p-value weighting methodology (Princessp: 'PRior-INformed, Convexly Constrained Spjotvoll') introduced by Edgar Dobrib…	Curated	Mathematical Methods	`AIMech:ConstrainedConvexPValueWeightingInMonotoneLikelihoodRatioFamilies`	4 claims 3 sources
Constrained L1 Minimization for Sparse Precision Matrix Estimation aka CLIME, Constrained L1-Minimization for Inverse Matrix Estimation… A high-dimensional sparse inverse covariance (precision) matrix estimation and graphical model selection methodology (CLIME) that solves the…	Curated	Mathematical Methods	`AIMech:ConstrainedL1MinimizationForSparsePrecisionMatrixEstimation`	3 claims 3 sources
Consumer Bias An individual bias arising when an algorithm or platform provides users a venue to express their biases occurring from either side in a digi…	AIO	Bias	`AIO:ConsumerBias`	Imported
Content Production Bias A use and interpretation bias arising from structural lexical semantic and syntactic differences in user-generated content.	AIO	Bias	`AIO:ContentProductionBias`	Imported
Contention Resolution Schemes and Multilinear Relaxation Rounding for Constrained Submodular Maximization aka Contention Resolution Scheme, Monotone (b, c)-Balanced Contention Resolution Scheme… A (b, c)-balanced Contention Resolution (CR) scheme pi for a polyhedral relaxation P_I subseteq [0, 1]^N of a downward-closed independence f…	Curated	Algorithms	`AIMech:ContentionResolutionSchemesForSubmodularMaximization`	3 claims 3 sources
Context-sensitive emission hidden Markov model A hidden-state sequence-model family with a first-order Markov prior whose observation distributions depend jointly on hidden states at mult…	Curated	Model Families	`AIMech:ContextSensitiveEmissionHiddenMarkovModel`	1 claim 1 source
Continual Learning aka Incremental Learning, Life-Long Learning A deep neural network that learns sequential tasks without forgetting knowledge from preceding tasks and without access to old task data dur…	AIO	Network	`AIO:ContinualLearning`	Imported
Continual Learning LLM aka CL-Large Language Model, Continual Learning Large Language Model… A large language model that continually acquires new knowledge and skills over time without forgetting previously learned information allowi…	AIO	Model	`AIO:ContinualLearningLLM`	Imported
Continuous Coin Betting Optimizer aka COCOB, COntinuous COin Betting… A learning-rate-free, dual-averaging stochastic subgradient optimization algorithm that reduces d-dimensional minimization of a function F(w…	Curated	Algorithms	`AIMech:CocobContinuousCoinBettingOptimizer`	4 claims 3 sources
Continuous Greedy and Multilinear Extension for Matroid-Constrained Monotone Submodular Maximization aka Calinescu-Chekuri-Pal-Vondrak Continuous Greedy Algorithm, Multilinear Extension and Matroid Pipage Rounding… Continuous Greedy and Multilinear Extension for Matroid-Constrained Monotone Submodular Maximization is a two-stage continuous relaxation an…	Curated	Algorithms	`AIMech:ContinuousGreedyAndMultilinearExtensionForMatroidSubmodularMaximization`	3 claims 3 sources
Continuous-time Bayesian network A finite-state continuous-time model family combining a separate initial Bayesian-network distribution with a directed, possibly cyclic grap…	Curated	Model Families	`AIMech:ContinuousTimeBayesianNetwork`	6 claims 1 source
Contrastive divergence aka CD, CD-k A parameter-learning algorithm for energy-based or product-of-experts models that replaces the equilibrium negative-phase expectation by con…	Curated	Algorithms	`AIMech:ContrastiveDivergence`	2 claims 3 sources
Contrastive Learning A deep neural network self-supervised learning approach that learns to distinguish between similar and dissimilar data samples.	AIO	Network	`AIO:ContrastiveLearning`	Imported
Contrastive Learning LLM aka Representation learning A large language model that is trained to pull semantically similar samples closer together and push dissimilar samples apart in the represe…	AIO	Model	`AIO:ContrastiveLearningLLM`	Imported
Contrastive predictive coding aka CPC A representation-learning procedure that encodes observations, summarizes preceding representations as context, and jointly trains these com…	Curated	Algorithms	`AIMech:ContrastivePredictiveCoding`	1 claim 2 sources
Controllable LLM aka Controllable Large Language Model, conditional generation… A large language model that allows for explicit control over certain attributes of the generated text such as style tone topic or other desi…	AIO	Model	`AIO:ControllableLLM`	Imported
Convex and Nonconvex Optimization Bridging for Robust PCA under Noise, Outliers, and Missing Data aka Convex-Nonconvex Bridging for Noisy Robust PCA, Chen-Fan-Ma-Yan Primal-Dual Bridging for Principal Component Pursuit… A unified convex–nonconvex optimization analysis and estimation framework (introduced by Yuxin Chen, Jianqing Fan, Cong Ma, and Yuling Yan i…	Curated	Mathematical Methods	`AIMech:ConvexAndNonconvexBridgingForRobustPCAUnderNoiseOutliersAndMissingData`	3 claims 3 sources
ConvLSTM1D Layer A convolutional layer that implements a 1D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.	AIO	Layer	`AIO:ConvLSTM1DLayer`	Imported
ConvLSTM2D Layer A convolutional layer that implements a 2D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.	AIO	Layer	`AIO:ConvLSTM2DLayer`	Imported
ConvLSTM3D Layer A convolutional layer that implements a 3D Convolutional LSTM similar to an LSTM but with convolutional input and recurrent transformations.	AIO	Layer	`AIO:ConvLSTM3DLayer`	Imported
Convolution1D Layer aka Conv1D, Conv1D Layer… A convolutional layer that implements 1D convolution (e.g. temporal convolution).	AIO	Layer	`AIO:Convolution1DLayer`	Imported
Convolution1DTranspose Layer aka Conv1DTranspose Layer, ConvTranspose1D… A convolutional layer that implements transposed 1D convolution sometimes called deconvolution.	AIO	Layer	`AIO:Convolution1DTransposeLayer`	Imported
Convolution2D Layer aka Conv2D, Conv2D Layer… A convolutional layer that implements 2D convolution (e.g. spatial convolution over images).	AIO	Layer	`AIO:Convolution2DLayer`	Imported
Convolution2DTranspose Layer aka Conv2DTranspose Layer, ConvTranspose2D… A convolutional layer that implements transposed 2D convolution	AIO	Layer	`AIO:Convolution2DTransposeLayer`	Imported
Convolution3D Layer aka Conv3D, Conv3D Layer… A convolutional layer that implements 3D convolution (e.g. spatial convolution over volumes).	AIO	Layer	`AIO:Convolution3DLayer`	Imported
Convolution3DTranspose Layer aka Conv3DTranspose Layer, ConvTranspose3D… A convolutional layer that implements transposed 3D convolution	AIO	Layer	`AIO:Convolution3DTransposeLayer`	Imported
Convolutional Block Attention Module aka CBAM A convolutional feature refinement component that sequentially applies learned channel attention and then spatial attention to an intermedia…	Curated	Layers & Modules	`AIMech:ConvolutionalBlockAttentionModule`	2 claims 2 sources
Convolutional Layer A layer that contains a set of filters (or kernels) parameters of which are to be learned throughout the training.	AIO	Layer	`AIO:ConvolutionalLayer`	Imported
Convpass aka Convolutional Bypasses, Convpass_attn… A vision-oriented parameter-efficient transfer learning architecture (Convolutional Bypasses) for Vision Transformers that inserts trainable…	Curated	Architectures	`AIMech:ConvPass`	3 claims 3 sources
Coordinate-wise Median and Trimmed Mean Byzantine-Robust Distributed Learning aka Coordinate-wise Median Gradient Descent, Coordinate-wise Trimmed Mean Gradient Descent… A family of dimension-separable robust gradient and parameter aggregation algorithms for Byzantine-resilient distributed optimization across…	Curated	Algorithms	`AIMech:CoordinateWiseMedianAndTrimmedMeanByzantineRobustDistributedLearning`	4 claims 3 sources
Core vector machine aka CVM An approximate kernel training algorithm that reformulates supported constant-diagonal simplex quadratic programs as minimum enclosing balls…	Curated	Algorithms	`AIMech:CoreVectorMachine`	8 claims 4 sources
Core vector regression aka CVR A support-vector regression training algorithm that approximates a penalized-bias, paired squared-slack formulation with a learned unconstra…	Curated	Algorithms	`AIMech:CoreVectorRegression`	6 claims 2 sources
Core-set support vector data description aka CSVDD An approximate one-class training algorithm that grows a core subset using the nearest expanded-sphere violator, refits support vector data…	Curated	Algorithms	`AIMech:CoreSetSupportVectorDataDescription`	7 claims 1 source
Correlated topic model aka CTM A mixed-membership topic model that draws each document's topic proportions from a logistic-normal distribution and generates its words thro…	Curated	Model Families	`AIMech:CorrelatedTopicModel`	2 claims 3 sources
Correlation-based Hammerstein identification A two-stage identification algorithm for a real-valued single-input single-output polynomial Hammerstein cascade that estimates a scaled lin…	Curated	Algorithms	`AIMech:CorrelationBasedHammersteinIdentification`	4 claims 2 sources
Correlation-based Wiener identification A two-stage identification algorithm for a real-valued single-input single-output polynomial Wiener cascade that estimates a scaled linear r…	Curated	Algorithms	`AIMech:CorrelationBasedWienerIdentification`	4 claims 2 sources
Corrupted Sensing Convex Signal-Corruption Demixing and Subdifferential Distance Bounds aka Corrupted Sensing Signal-Corruption Separation via Convex Programming, Foygel-Mackey Constrained and Penalized Corrupted Sensing Guarantees… Corrupted Sensing Convex Signal-Corruption Demixing and Subdifferential Distance Bounds is a convex recovery and Gaussian-width analysis fra…	Curated	Mathematical Methods	`AIMech:CorruptedSensingConvexSignalCorruptionDemixingAndSubdifferentialDistanceBounds`	3 claims 3 sources
CoSaMP (Compressive Sampling Matching Pursuit) aka CoSaMP, Compressive Sampling Matching Pursuit… CoSaMP (Compressive Sampling Matching Pursuit) is an iterative greedy-pursuit signal reconstruction algorithm introduced by Needell and Trop…	Curated	Algorithms	`AIMech:CoSaMPCompressiveSamplingMatchingPursuit`	3 claims 3 sources
COSTA Contrastive Span Prediction Pre-Training for Dense Retrieval aka COSTA, Contrastive Span Prediction for Dense Retrieval… A decoder-free self-supervised pre-training algorithm for dense text retrieval that samples T spans at each of four granularities (word, phr…	Curated	Algorithms	`AIMech:COSTAContrastiveSpanPredictionForDenseRetrieval`	4 claims 3 sources
CoT-MAE Contextual Masked Auto-Encoder for Dense Passage Retrieval aka CoT-MAE, ConTextual Masked Auto-Encoder… An asymmetric encoder-decoder generative pre-training architecture and algorithm for dense passage retrieval that samples pairs of text span…	Curated	Architectures	`AIMech:CoTMAEContextualMaskedAutoEncoderForDensePassageRetrieval`	4 claims 3 sources
Counterfactual fairness aka CF (counterfactual fairness) A fairness criterion in a specified causal model requiring a predictor's conditional output distribution, given an individual's observed att…	Curated	Evaluation Criteria	`AIMech:CounterfactualFairness`	3 claims 3 sources
CountSketch Input-Sparsity Subspace Embedding and Regression aka Clarkson-Woodruff Input-Sparsity Transform (CW Sketch), Sparse CountSketch Oblivious Subspace Embedding… CountSketch Input-Sparsity Subspace Embedding and Regression is an oblivious sparse random projection and numerical linear algebra framework…	Curated	Algorithms	`AIMech:CountSketchInputSparsitySubspaceEmbeddingAndRegression`	3 claims 3 sources
Covariance Matrix Adaptation Evolution Strategy aka CMA-ES An evolution strategy for continuous optimization that samples a multivariate normal search distribution and adapts its mean, covariance and…	Curated	Algorithms	`AIMech:CovarianceMatrixAdaptationEvolutionStrategy`	1 claim 1 source
Covariate-powered cross-weighted multiple testing aka Independent Hypothesis Weighting (IHW), Cross-Weighted Benjamini-Hochberg Procedure (IHW-BH)… A covariate-assisted multiple-testing methodology (Ignatiadis & Huber 2021, Journal of the Royal Statistical Society: Series B 83(4):720-751…	Curated	Mathematical Methods	`AIMech:CovariatePoweredCrossWeightedMultipleTesting`	4 claims 3 sources
Crank–Nicolson Langevin sampling aka CNL A Metropolis-corrected Gaussian-reference sampler that combines a Crank–Nicolson treatment of the reference precision with an explicit gradi…	Curated	Algorithms	`AIMech:CrankNicolsonLangevin`	1 claim 1 source
Crank–Nicolson Metropolis sampling aka CN sampler A Metropolis sampler for a Gaussian-reference target using a Crank–Nicolson discretization of the unpreconditioned reference Ornstein–Uhlenb…	Curated	Algorithms	`AIMech:CrankNicolsonMetropolis`	1 claim 1 source
CRFL Certifiably Robust Federated Learning via Parameter Clipping and Smoothing aka CRFL, Certifiably Robust Federated Learning against Backdoor Attacks… A certifiably backdoor-robust federated learning framework that clips the l2 norm of the server-aggregated global model parameters Clip_{rho…	Curated	Algorithms	`AIMech:CrflCertifiablyRobustFederatedLearningViaParameterClippingAndSmoothing`	4 claims 3 sources
Cropping1D Layer A reshaping layer that crops along the time dimension (axis 1) for 1D input.	AIO	Layer	`AIO:Cropping1DLayer`	Imported
Cropping2D Layer A layer that crops along spatial dimensions (i.e. height and width) for 2D input.	AIO	Layer	`AIO:Cropping2DLayer`	Imported
Cropping3D Layer A layer that crops along spatial dimensions (depth, height and width) for 3D input.	AIO	Layer	`AIO:Cropping3DLayer`	Imported
Cross-Domain LLM aka Domain-General LLM, cross-domain transfer… A large language model that performs well across a wide range of domains without significant loss in performance, facilitated by advanced do…	AIO	Model	`AIO:CrossDomainLLM`	Imported
Cross-entropy optimization aka Cross-entropy method for optimization A stochastic optimization method that iteratively samples a parameterized search distribution, selects high-performing samples using an adap…	Curated	Algorithms	`AIMech:CrossEntropyOptimization`	1 claim 1 source
Cross-entropy rare-event importance sampling A rare-event probability estimation algorithm that fits a parametric importance-sampling proposal by cross-entropy minimization toward the n…	Curated	Algorithms	`AIMech:CrossEntropyImportanceSampling`	6 claims 1 source
Cross-validated prior-likelihood conflict diagnostic A Bayesian hierarchical-model diagnostic that leaves an assessed unit out of population-parameter fitting, generates predictive-prior and re…	Curated	Algorithms	`AIMech:CrossValidatedPriorLikelihoodConflictDiagnostic`	7 claims 3 sources
CSER (Communication-Efficient SGD with Error Reset) aka CSER, Communication-Efficient SGD with Error Reset… A communication-efficient distributed SGD algorithm (and Nesterov momentum variant M-CSER) that adapts a pair of delta-approximate compresso…	Curated	Algorithms	`AIMech:CSERCommunicationEfficientSgdWithErrorReset`	4 claims 3 sources
CTAugment An online augmentation-policy adaptation procedure that samples image operations and adjusts their parameter-selection weights using classif…	Curated	Algorithms	`AIMech:CTAugment`	2 claims 6 sources
CURE clustering aka CURE, Clustering Using REpresentatives An agglomerative clustering procedure that represents each cluster by several scattered points shrunk toward its mean and merges the pair wi…	Curated	Algorithms	`AIMech:CUREClustering`	1 claim 1 source
Curriculum Dropout A neural-network training procedure that starts without unit suppression and gradually increases Bernoulli dropout by decreasing the probabi…	Curated	Algorithms	`AIMech:CurriculumDropout`	5 claims 2 sources
Curriculum Learning aka Sequential Learning, Structured Learning… A training strategy in machine learning where models are trained on data in a meaningful order starting with simpler examples and gradually…	AIO	TrainingStrategy	`AIO:CurriculumLearning`	Imported
Curriculum Learning LLM aka Learning progression A large language model that is trained by presenting learning examples in a meaningful order from simple to complex mimicking the learning t…	AIO	Model	`AIO:CurriculumLearningLLM`	Imported
CutMix A training augmentation procedure that replaces a rectangular region of one image with the corresponding region of another and mixes their c…	Curated	Algorithms	`AIMech:CutMix`	2 claims 2 sources
Cutout A training-image augmentation method that removes information from a randomly located square region by replacing that region with zeros in t…	Curated	Preprocessing Methods	`AIMech:Cutout`	1 claim 1 source
Cutting Plane Multiclass Maximum Margin Clustering aka CPM3C A fixed-kernel multiclass clustering procedure that fits latent winning-class margins by adding violated aggregate constraints and repeatedl…	Curated	Algorithms	`AIMech:CuttingPlaneMulticlassMaximumMarginClustering`	4 claims 1 source
D-Adaptation (Learning-Rate-Free Optimization by Distance Lower Bounding) aka D-Adaptation, D-Adapted AdaGrad… A hyperparameter-free (learning-rate-free) optimization framework (Algorithms 1-5) for minimizing convex G-Lipschitz and deep learning objec…	Curated	Algorithms	`AIMech:DAdaptationLearningRateFreeOptimization`	4 claims 3 sources
D2 (Decentralized Training over Decentralized Heterogeneous Data) aka D2, D^2 Decentralized Training over Decentralized Data… A heterogeneity-invariant decentralized stochastic optimization algorithm (Tang et al. 2018, Section 4, Algorithm 1, Equation 3) over a symm…	Curated	Algorithms	`AIMech:D2VarianceReducedDecentralizedTrainingOverHeterogeneousData`	4 claims 3 sources
DART Differentiable Prompt Few-Shot Tuning aka DART, DifferentiAble pRompT… A few-shot prompt-based fine-tuning algorithm that maps both template tokens {[T_{0:i}], [MASK], [T_{i+1:m}]} and target class labels M(Y_j)…	Curated	Algorithms	`AIMech:DARTDifferentiablePromptFewShotTuning`	4 claims 3 sources
Data Augmentation aka Data Enrichment, Data Expansion… A data enhancement used to increase the diversity and quantity of training data by applying various transformations such as rotation scaling…	AIO	Preprocessing	`AIO:DataAugmentation`	Imported
Data Dredging Bias aka Data Dredging A use and interpretation bias where testing many hypotheses in a dataset may yield apparent statistical significance even when results are n…	AIO	Bias	`AIO:DataDredgingBias`	Imported
Data Generation Bias A selection and sampling bias arising from adding synthetic or redundant data samples to a dataset.	AIO	Bias	`AIO:DataGenerationBias`	Imported
Data Imputation A machine learning task focused on methods that replace missing data with substituted values.	AIO	MachineLearningTask	`AIO:DataImputation`	Imported
Data Persistence Bias aka Retrospective Data Persistence Bias, Social Media Data Persistence Bias… A systematic dataset representation and survivorship bias that arises when user-generated or web data is collected retrospectively at a time…	Curated	Biases	`AIMech:DataPersistenceBias`	4 claims 3 sources
Data Preparation aka Data Assembly, Data Curation… A preprocessing that cleans, transforms and organizes raw data into a suitable format for analysis and modeling, ensuring the quality and re…	AIO	Preprocessing	`AIO:DataPreparation`	Imported
Data-to-Text LLM aka Meaning representation A large language model that generates natural language descriptions from structured data sources like tables, graphs, and knowledge bases, r…	AIO	Model	`AIO:DatatoTextLLM`	Imported
DataEnhancement A preprocessing used to improve the quality diversity and volume of data available for training machine learning models, such as data augmen…	AIO	Preprocessing	`AIO:DataEnhancement`	Imported
DBSCAN aka Density-Based Spatial Clustering of Applications with Noise Density-based clustering that connects dense neighborhoods and identifies unsupported observations as noise.	Curated	Algorithms	`AIMech:DBSCAN`	1 claim 1 source
DC-BERT (Decoupling Question and Document for Efficient Contextual Encoding) aka DC-BERT, Decoupled Contextual BERT… A decoupled contextual encoding framework for open-domain question answering document retrieval and reranking (Zhang, Nie, Geng, Ramamurthy,…	Curated	Architectures	`AIMech:DCBERTDecouplingQuestionAndDocumentForEfficientContextualEncoding`	4 claims 3 sources
DCD-PSGD and ECD-PSGD (Difference-Compression and Extrapolation-Compression Decentralized Parallel SGD) aka DCD-PSGD and ECD-PSGD, Difference Compression D-PSGD and Extrapolation Compression D-PSGD… A pair of communication-compressed decentralized parallel stochastic gradient descent algorithms over doubly stochastic gossip graphs W (Tan…	Curated	Algorithms	`AIMech:DcdPsgdAndEcdPsgdCompressedDecentralizedParallelStochasticGradientDescent`	4 claims 3 sources
De-biased Noisy Matrix Completion and De-shrunken Low-Rank Factor Uncertainty Quantification aka De-biased Matrix Completion and De-shrunken Low-Rank Factor Estimator, Chen-Fan-Ma-Yan Noisy Matrix Completion Uncertainty Quantification… A unified statistical inference and uncertainty quantification methodology (introduced by Yuxin Chen, Jianqing Fan, Cong Ma, and Yuling Yan…	Curated	Mathematical Methods	`AIMech:DebiasedNoisyMatrixCompletionInferenceAndUncertaintyQuantification`	3 claims 3 sources
Decision Tree A classification that uses a tree-like model of decisions and their possible consequences including chance event outcomes resource costs and…	AIO	MachineLearningTask	`AIO:DecisionTree`	Imported
Decoder LLM A large language model that uses a decoder-only architecture consisting of only a decoder trained to predict the next token in a sequence gi…	AIO	Model	`AIO:DecoderLLM`	Imported
Decomposable Regularizer and Restricted Strong Convexity M-Estimator Framework aka A Unified Framework for High-Dimensional Analysis of M-Estimators with Decomposable Regularizers (Negahban, Ravikumar, Wainwright, & Yu 2012), Subspace-Decomposable Regularizer and Restricted Strong Convexity M-Estimation Theory… Decomposable Regularizer and Restricted Strong Convexity M-Estimator Framework is a non-asymptotic high-dimensional statistical analysis met…	Curated	Mathematical Methods	`AIMech:DecomposableRegularizerAndRestrictedStrongConvexityMEstimatorFramework`	3 claims 4 sources
Deconvolutional Network aka DN A deep neural network that uses deconvolution for unsupervised construction of hierarchical image representations.	AIO	Network	`AIO:DeconvolutionalNetwork`	Imported
Decorrelated Score Function and One-Step Estimator for Sparse High-Dimensional Inference aka Decorrelated Score Test, High-Dimensional Decorrelated Score Function… A general hypothesis-testing and confidence-region methodology (introduced by Yang Ning and Han Liu in 2017) for a low-dimensional or growin…	Curated	Algorithms	`AIMech:DecorrelatedScoreFunctionAndOneStepEstimatorForSparseHighDimensionalInference`	3 claims 3 sources
DeeBERT (Dynamic Early Exiting for Accelerating BERT Inference) aka DeeBERT, Dynamic Early Exiting for Accelerating BERT Inference… DeeBERT (Dynamic Early Exiting for Accelerating BERT Inference) is a dynamic multi-exit fine-tuning and inference method for pretrained Tran…	Curated	Algorithms	`AIMech:DeeBERTDynamicEarlyExitingForAcceleratingBERTInference`	4 claims 3 sources
Deep Active Learning aka DeepAL A deep neural network that combines deep learning and active learning to maximize model performance while annotating the fewest samples poss…	AIO	Network	`AIO:DeepActiveLearning`	Imported
Deep autoregressive network aka DARN A generative neural architecture that combines directed stochastic hidden layers with autoregressive within-layer conditional dependencies a…	Curated	Architectures	`AIMech:DeepAutoregressiveNetwork`	1 claim 1 source
Deep Belief Network aka DBN An unsupervised pretrained network composed of multiple layers of latent variables that learns to probabilistically reconstruct inputs and p…	AIO	Network	`AIO:DeepBeliefNetwork`	Imported
Deep continuous clustering A clustering algorithm that jointly learns a nonlinear autoencoder and one latent representative per observation by combining reconstruction…	Curated	Algorithms	`AIMech:DeepContinuousClustering`	7 claims 7 sources
Deep Convolutional Inverse Graphics Network aka DCIGN An autoencoder network that learns interpretable disentangled image representations through convolution and de-convolution layers trained wi…	AIO	Network	`AIO:DeepConvolutionalInverseGraphicsNetwork`	Imported
Deep Convolutional Network aka CNN, ConvNet… A deep neural network specialized for analyzing visual imagery using shared-weight architecture and translation-equivariant feature maps.	AIO	Network	`AIO:DeepConvolutionalNetwork`	Imported
Deep deterministic policy gradient aka DDPG An off-policy actor–critic method for continuous control using neural function approximators and deterministic policy gradients.	Curated	Algorithms	`AIMech:DeepDeterministicPolicyGradient`	1 claim 1 source
Deep embedded clustering aka DEC, Unsupervised deep embedding for clustering analysis A neural clustering procedure that jointly refines an embedding and cluster centers by fitting Student-t soft assignments to periodically re…	Curated	Algorithms	`AIMech:DeepEmbeddedClustering`	1 claim 2 sources
Deep Feed-Forward Network aka DFF, MLP… A deep neural network that processes information in one direction—from input nodes through hidden nodes to output nodes—without cycles or lo…	AIO	Network	`AIO:DeepFeedForwardNetwork`	Imported
Deep Gradient Compression (DGC with Momentum Correction and Momentum Factor Masking) aka Deep Gradient Compression, DGC… A high-sparsity distributed gradient compression algorithm (Lin et al. 2018, Section 3, Algorithm 1) that transmits only the top-k magnitude…	Curated	Algorithms	`AIMech:DeepGradientCompressionWithMomentumCorrection`	4 claims 3 sources
Deep InfoMax aka DIM A representation-learning procedure that jointly trains an encoder and a dependence critic on matched versus mismatched global or local-to-g…	Curated	Algorithms	`AIMech:DeepInfoMax`	1 claim 5 sources
Deep Kernel Shaping for Normalizer-Free and Skip-Free Deep Neural Networks aka Deep Kernel Shaping, DKS… A model-class-preserving neural network initialization and activation-function transformation method introduced by Martens et al. (2021) tha…	Curated	Mathematical Methods	`AIMech:DeepKernelShapingForNormalizerFreeAndSkipFreeDeepNeuralNetworks`	4 claims 3 sources
Deep Neural Network aka DNN An artificial neural network characterized by multiple hidden layers between the input and output layers.	AIO	Network	`AIO:DeepNeuralNetwork`	Imported
Deep Output Recurrent Neural Network aka DO-RNN A recurrent neural architecture whose hidden-to-output function uses a multilayer perceptron with intermediate nonlinear feedforward layers…	Curated	Architectures	`AIMech:DeepOutputRecurrentNeuralNetwork`	4 claims 1 source
Deep Output-Transition Recurrent Neural Network aka DOT-RNN, Deep output, deep transition RNN A recurrent neural architecture that uses intermediate nonlinear feedforward layers in both the hidden-state transition from the previous st…	Curated	Architectures	`AIMech:DeepOutputTransitionRecurrentNeuralNetwork`	6 claims 1 source
Deep Q-network learning aka DQN, Deep Q-network A deep Q-learning method that trains a neural action-value function using replayed transitions and a separate target network.	Curated	Algorithms	`AIMech:DeepQNetwork`	1 claim 1 source
Deep Sets A neural architecture family for unordered collections that combines shared element transformations with symmetric aggregation for invariant…	Curated	Architectures	`AIMech:DeepSets`	1 claim 1 source
Deep Sets++ aka DS++ A Deep Sets architecture revision whose encoder combines identity residual paths with set normalization while retaining the original aggrega…	Curated	Architectures	`AIMech:DeepSetsPlusPlus`	1 claim 1 source
Deep SHAP A compositional approximation of neural-network Shapley attributions using component-level SHAP values and backward multipliers.	Curated	Algorithms	`AIMech:DeepSHAP`	1 claim 1 source
Deep Transfer Learning A deep neural network that relaxes the hypothesis that training data must be independent and identically distributed with test data to addre…	AIO	Network	`AIO:DeepTransferLearning`	Imported
Deep Transition Recurrent Neural Network aka DT-RNN A recurrent neural architecture whose state-transition function uses a multilayer perceptron with intermediate nonlinear feedforward layers…	Curated	Architectures	`AIMech:DeepTransitionRecurrentNeuralNetwork`	4 claims 1 source
DeepCluster aka Deep clustering for unsupervised learning of visual features A visual representation-learning procedure that alternates clustering current neural features into pseudo-labels and training the feature ex…	Curated	Algorithms	`AIMech:DeepCluster`	1 claim 4 sources
DeepCT Deep Contextualized Term Weighting for First-Stage Retrieval aka DeepCT, DeepCT-Index and DeepCT-Query… A supervised deep contextualized term-weighting framework for first-stage bag-of-words retrieval that maps each word's first-subword context…	Curated	Algorithms	`AIMech:DeepCTContextAwareTermImportanceEstimationForFirstStageRetrieval`	4 claims 3 sources
DeepImpact Learning Passage Impacts for Inverted Indexes aka DeepImpact, Learning Passage Impacts for Inverted Indexes… A learned sparse impact-scoring and inverted-index retrieval method that expands each passage offline with DocT5Query predicted queries conc…	Curated	Algorithms	`AIMech:DeepImpactLearningPassageImpactsForInvertedIndexes`	4 claims 3 sources
DeepLIFT aka Deep Learning Important FeaTures A neural-network attribution method that distributes an output's difference from a reference activation to input differences using backward…	Curated	Algorithms	`AIMech:DeepLIFT`	1 claim 1 source
Definition-filtered Girvan–Newman community detection aka self-contained Girvan–Newman algorithm, strong/weak community validation for Girvan–Newman A Girvan–Newman variant that retains a branching event in the reported hierarchy only when at least two resulting groups satisfy a selected…	Curated	Algorithms	`AIMech:DefinitionFilteredGirvanNewman`	6 claims 1 source
Degree-Corrected Stochastic Blockmodel and Edge-Stub Kullback-Leibler Divergence Profile Log-Likelihood aka Degree-Corrected Stochastic Blockmodel (DC-SBM), Karrer-Newman Degree-Corrected Stochastic Blockmodel… Degree-Corrected Stochastic Blockmodel and Edge-Stub Kullback-Leibler Divergence Profile Log-Likelihood is a generative random multigraph mo…	Curated	Mathematical Methods	`AIMech:DegreeCorrectedStochasticBlockmodelAndEdgeStubKLDivergenceProfileLikelihood`	3 claims 3 sources
DEHB aka Evolutionary Hyperband A hyperparameter optimization algorithm that combines Hyperband resource schedules with differential-evolution populations at different reso…	Curated	Algorithms	`AIMech:DEHB`	1 claim 2 sources
Delayed-rejection adaptive Metropolis aka DRAM An adaptive Metropolis procedure combining history-based Gaussian proposal covariance updates between transitions with corrected delayed-rej…	Curated	Algorithms	`AIMech:DelayedRejectionAdaptiveMetropolis`	1 claim 2 sources
Delayed-rejection Metropolis aka Delayed rejection Metropolis-Hastings A Metropolis-Hastings sampling procedure that can propose another candidate after rejection within the same transition, correcting acceptanc…	Curated	Algorithms	`AIMech:DelayedRejectionMetropolis`	1 claim 1 source
Delta-LoRA aka Delta Low-Rank Adaptation, Delta-LoRA High-Rank Parameter Fine-Tuning A parameter-efficient fine-tuning algorithm that simultaneously optimizes a pair of low-rank adapter matrices with an adaptive optimizer and…	Curated	Algorithms	`AIMech:DeltaLoRA`	4 claims 3 sources
Demand-Execution CoPE scheduling A computation-focused CoPE next-action schema that consults a supplied computation allocator and substitutes a required head action when its…	Curated	Algorithms	`AIMech:DemandExecutionCoPE`	3 claims 2 sources
Demographic parity aka Statistical parity A group-level prediction criterion requiring the distribution of a decision or prediction to be independent of a specified protected attribu…	Curated	Evaluation Criteria	`AIMech:DemographicParity`	3 claims 3 sources
Denoising Auto Encoder aka DAE, Denoising Autoencoder An autoencoder network trained to reconstruct the original undistorted input from a partially corrupted input.	AIO	Network	`AIO:DenoisingAutoEncoder`	Imported
Dense Layer A layer that is a regular densely-connected neural network layer.	AIO	Layer	`AIO:DenseLayer`	Imported
DenseFeatures Layer A layer that produces a dense tensor based on given feature columns.	AIO	Layer	`AIO:DenseFeaturesLayer`	Imported
DensePhrases Dense Phrase Retrieval at Scale aka DensePhrases, Learning Dense Representations of Phrases at Scale… A reader-free, purely dense phrase-retrieval architecture and training framework for open-domain question answering and knowledge-intensive…	Curated	Architectures	`AIMech:DensePhrasesLearningDenseRepresentationsOfPhrasesAtScale`	4 claims 3 sources
Deployment Bias A group bias arising when systems are used as decision aids for humans since the human intermediary may act on predictions in ways that are…	AIO	Bias	`AIO:DeploymentBias`	Imported
Depth-first iterative deepening aka DFID, Iterative deepening depth-first search… A search algorithm that repeatedly performs depth-first searches from the start with successively larger depth limits, redoing shallower wor…	Curated	Algorithms	`AIMech:DepthFirstIterativeDeepening`	2 claims 2 sources
Depth-first search aka DFS, Depth first traversal A graph or state-space traversal that follows a newly chosen successor down the current search branch and backtracks when that branch has no…	Curated	Algorithms	`AIMech:DepthFirstSearch`	2 claims 2 sources
Depth-Gated LSTM aka DGLSTM, Depth-gated long short-term memory A stacked LSTM architecture that adds a learned, elementwise gated contribution from the current lower-layer memory cell to the upper-layer…	Curated	Architectures	`AIMech:DepthGatedLSTM`	6 claims 1 source
DepthwiseConv1D Layer A convolutional layer that performs depthwise 1D convolution	AIO	Layer	`AIO:DepthwiseConv1DLayer`	Imported
DepthwiseConv2D Layer A convolutional layer that performs depthwise 2D convolution	AIO	Layer	`AIO:DepthwiseConv2DLayer`	Imported
Derivative-observation Gaussian process regression aka Gaussian process regression with derivative observations A Gaussian-process regression procedure that jointly conditions a sufficiently differentiable scalar-function prior on function values and p…	Curated	Algorithms	`AIMech:DerivativeObservationGaussianProcessRegression`	5 claims 1 source
DeTAG Decentralized Stochastic Gradient Tracking with By-Phase Accelerated Gossip aka DeTAG, Decentralized Stochastic Gradient Tracking with By-Phase Accelerated Gossip… A decentralized stochastic non-convex optimization algorithm (DeTAG) that partitions training into phases of length R, concurrently executin…	Curated	Algorithms	`AIMech:DetagDecentralizedStochasticGradientTrackingWithByPhaseAcceleratedGossip`	4 claims 3 sources
Detection Bias A selection and sampling bias characterized by systematic differences between groups in how outcomes are determined potentially over- or und…	AIO	Bias	`AIO:DetectionBias`	Imported
Deterministic Annealing Expectation Maximization aka Deterministic Annealing EM, DAEM A latent-variable likelihood-fitting procedure that performs deterministic powered-posterior EM updates along a warm-started cooling schedul…	Curated	Algorithms	`AIMech:DeterministicAnnealingExpectationMaximization`	4 claims 1 source
Deterministic Banach contraction and Newton-Kantorovich inequalities for smooth M-estimators aka Banach Contraction Inversion and Semilocal Newton-Kantorovich Bahadur Expansions for M-Estimators, Generalized Self-Concordant Hessian-Ratio C(u, w) Deterministic M-Estimation Inequalities… Deterministic Banach contraction and Newton-Kantorovich inequalities for smooth M-estimators are a finite-sample, assumption-free analytical…	Curated	Mathematical Methods	`AIMech:DeterministicBanachContractionAndNewtonKantorovichInequalitiesForSmoothMEstimators`	4 claims 2 sources
DETOX Redundancy-Based Hierarchical Byzantine-Robust Gradient Aggregation aka DETOX, DETOX Hierarchical Robust Aggregation… A two-stage Byzantine-resilient distributed gradient aggregation framework that partitions p compute nodes into hat_p = p/r node groups of s…	Curated	Algorithms	`AIMech:DetoxRedundancyBasedHierarchicalByzantineRobustGradientAggregation`	3 claims 3 sources
Diaconis–Holmes–Neal fiber sampler A finite-state Metropolis sampler that uses partitions into ordered lines, retains a binary direction for each partition, and combines a nei…	Curated	Algorithms	`AIMech:DiaconisHolmesNealFiberSampler`	6 claims 1 source
Diagonal structured state space model aka S4D A diagonal state-space sequence-model family that computes its discretized convolution kernel by a Vandermonde product, with explicit choice…	Curated	Model Families	`AIMech:S4D`	1 claim 1 source
Diagonal Thresholding and Semidefinite Relaxation Support Recovery for Sparse Principal Components aka Amini-Wainwright Primal-Dual Witness SDP and Diagonal Thresholding Sparse PCA Analysis, High-Dimensional Spiked Covariance Support Recovery via SDP Relaxation and Diagonal Screening… Diagonal Thresholding and Semidefinite Relaxation Support Recovery for Sparse Principal Components is a high-dimensional sparse eigenvector…	Curated	Mathematical Methods	`AIMech:DiagonalThresholdingAndSemidefiniteRelaxationSupportRecoveryForSparsePCA`	3 claims 3 sources
Dialogue LLM aka Dialogue Large Language Model, conversational AI… A large language model that is optimized for engaging in multi-turn conversations understanding context and generating relevant coherent res…	AIO	Model	`AIO:DialogueLLM`	Imported
DIANA Distributed Learning with Compressed Gradient Differences aka DIANA, Distributed Learning with Compressed Gradient Differences… A distributed composite and nonconvex stochastic optimization algorithm (DIANA) for minimizing f(x) + R(x) = (1/n) sum_{i=1}^n f_i(x) + R(x)…	Curated	Algorithms	`AIMech:DianaDistributedLearningWithCompressedGradientDifferences`	4 claims 3 sources
Diff Pruning aka Structured Diff Pruning, Adaptive Diff Pruning… A parameter-efficient transfer learning algorithm that formulates task-specific fine-tuning as learning a sparse difference ('diff') vector…	Curated	Algorithms	`AIMech:DiffPruning`	3 claims 3 sources
Differentiable LLM aka Differentiable Large Language Model, end-to-end training… A large language model that has an architecture amenable to full end-to-end training via backpropagation without relying on teacher forcing…	AIO	Model	`AIO:DifferentiableLLM`	Imported
Differentiable scheduled sampling A scheduled-sampling training procedure that replaces discrete model-feedback embeddings with differentiable soft mixtures, allowing later s…	Curated	Algorithms	`AIMech:DifferentiableScheduledSampling`	6 claims 1 source
Differential Evolution aka DE A population-based continuous optimization method that generates trial vectors using scaled differences between population members, combines…	Curated	Algorithms	`AIMech:DifferentialEvolution`	1 claim 1 source
diffGrad aka Difference of Gradients Adaptive Optimization, Dynamic Friction Sigmoid Adaptive Moment Estimation… A first-order adaptive stochastic gradient optimization algorithm that modulates Adam's bias-corrected parameter update by an element-wise d…	Curated	Algorithms	`AIMech:DiffGrad`	4 claims 3 sources
Diffusion Maps aka Diffusion Map A family of spectral embedding algorithms that normalizes a nonnegative symmetric affinity kernel into a reversible Markov operator and repr…	Curated	Algorithms	`AIMech:DiffusionMaps`	1 claim 1 source
DIGing and Push-DIGing (Distributed Inexact Gradient Tracking Over Time-Varying Graphs) aka DIGing and Push-DIGing, Distributed Inexact Gradient Tracking… A pair of geometrically convergent distributed gradient tracking algorithms over time-varying graphs (Nedic, Olshevsky, & Shi 2017, Sections…	Curated	Algorithms	`AIMech:DigingAndPushDigingDistributedInexactGradientTrackingOverTimeVaryingGraphs`	4 claims 3 sources
Dijkstra shortest-path algorithm aka Dijkstra's algorithm, Dijkstra shortest path A shortest-path algorithm for nonnegative edge weights that repeatedly settles the unsettled vertex with the smallest tentative distance fro…	Curated	Algorithms	`AIMech:DijkstraShortestPath`	2 claims 2 sources
Dimensionality Reduction aka Dimension Reduction An unsupervised learning focused on the process of transforming data from a high-dimensional space into a lower-dimensional space while reta…	AIO	MachineLearningTask	`AIO:DimensionalityReduction`	Imported
DINO self-distillation aka Self-distillation with no labels A self-supervised representation-learning procedure that matches cross-view student probabilities to centered and sharpened probabilities fr…	Curated	Algorithms	`AIMech:DINOSelfDistillation`	1 claim 2 sources
DIRECT global optimization A deterministic derivative-free global optimization algorithm that adaptively partitions a bounded real search box, samples rectangle center…	Curated	Algorithms	`AIMech:DIRECTGlobalOptimization`	6 claims 1 source
Direct preference optimization aka DPO Preference-based policy fitting using a classification objective on policy-to-reference probability ratios for preferred and dispreferred re…	Curated	Algorithms	`AIMech:DirectPreferenceOptimization`	1 claim 1 source
Dirichlet compound multinomial latent Dirichlet allocation aka DCM-LDA A topic-model family for grouped documents in which each group draws its own topic-word distributions from corpus-shared topic-specific Diri…	Curated	Model Families	`AIMech:DirichletCompoundMultinomialLDA`	3 claims 1 source
Discretization Layer A numerical features preprocessing layer which buckets continuous features by ranges.	AIO	Layer	`AIO:DiscretizationLayer`	Imported
Dispatch-dependent dual-queue planning A concurrent temporal-planning search procedure that alternates node expansion between a weighted goal-progress open list and a dispatch-con…	Curated	Algorithms	`AIMech:DispatchDependentDualQueuePlanning`	5 claims 1 source
Dispatch-dependent value functional A dispatch-prefix-conditioned mathematical rule that returns, as a function of a contemplated search start time t, the modeled probability o…	Curated	Mathematical Methods	`AIMech:DispatchDependentValueFunctional`	6 claims 1 source
DisPFL: Decentralized Sparse Training for Personalized Federated Learning aka DisPFL, Dis-PFL Decentralized Sparse PFL… A communication- and computation-efficient peer-to-peer personalized federated learning algorithm (DisPFL / Dis-PFL; Dai, Shen, He, Tian, an…	Curated	Algorithms	`AIMech:DisPflDecentralizedSparseTrainingForPersonalizedFederatedLearning`	4 claims 3 sources
DistilBERT: Knowledge Distillation During Pre-training aka DistilBERT, DistilBERT Triple-Loss Pre-training Distillation… A task-agnostic Transformer knowledge distillation paradigm that compresses a pre-trained bidirectional encoder during the pre-training phas…	Curated	Learning Paradigms	`AIMech:DistilBERTKnowledgeDistillationDuringPretraining`	4 claims 3 sources
Distillation aka Purification, Refining… A preprocessing that trains a smaller model to replicate the behavior of a larger model aiming to compress the knowledge into a more compact…	AIO	TrainingStrategy	`AIO:Distillation`	Imported
Distributed Principal Eigenspace Estimation by Subspace Projection Averaging aka Distributed PCA by Subspace Projection Averaging, Fan-Wang-Wang-Zhu Distributed Principal Eigenspace Estimator… A one-shot divide-and-conquer distributed principal component analysis algorithm and second-order subspace perturbation theory (introduced b…	Curated	Algorithms	`AIMech:DistributedPrincipalEigenspaceEstimationBySubspaceProjectionAveraging`	3 claims 3 sources
Ditto Fair and Robust Personalized Federated Multi-Task Learning aka Ditto, Ditto Personalized Federated Learning… A decoupled bi-level personalized federated multi-task learning framework (Ditto) that resolves the tension between cross-device performance…	Curated	Algorithms	`AIMech:DittoFairAndRobustPersonalizedFederatedMultiTaskLearning`	4 claims 3 sources
Diverse beam search aka DBS The inference procedure of Vijayakumar and colleagues that partitions a sequence beam budget into groups and updates each group using model…	Curated	Algorithms	`AIMech:DiverseBeamSearch`	3 claims 1 source
Divide-and-conquer beam search A memory-limited breadth-first heuristic search that discards least-promising open nodes when its chosen capacity is reached and recovers a…	Curated	Algorithms	`AIMech:DivideConquerBeamSearch`	3 claims 3 sources
Divide-and-conquer beam-stack search aka DCBSS A beam-stack search implementation that retains a small set of search layers and relay information, regenerates missing layers for backtrack…	Curated	Algorithms	`AIMech:DivideConquerBeamStackSearch`	2 claims 2 sources
Divide-and-Conquer Spectral Byzantine-Robust Aggregation aka DnC, DnC AGR… A Byzantine-robust gradient aggregation algorithm for federated learning that mitigates the curse of dimensionality and defeats optimization…	Curated	Algorithms	`AIMech:DncDivideAndConquerSpectralByzantineRobustAggregation`	3 claims 3 sources
Doc2query Neural Document Expansion by Query Prediction aka Doc2query, Document Expansion by Query Prediction… A neural document-expansion preprocessing method for first-stage information retrieval that trains a sequence-to-sequence Transformer model…	Curated	Preprocessing Methods	`AIMech:Doc2QueryDocumentExpansionByQueryPrediction`	4 claims 3 sources
Document NADE aka DocNADE A neural autoregressive document model that predicts successive words from shared additive embeddings of the preceding words, using normaliz…	Curated	Architectures	`AIMech:DocumentNADE`	1 claim 2 sources
DoG (Distance over Gradients Parameter-Free Step Size Schedule) aka DoG, Distance over Gradients… A parameter-free dynamic step-size schedule for stochastic gradient descent (x_{t+1} = x_t - eta_t g_t) that sets the initial step size to e…	Curated	Algorithms	`AIMech:DogDistanceOverGradientsParameterFreeStepSizeSchedule`	3 claims 3 sources
Domain Conditional Pointwise Mutual Information (PMI_DC) Scoring aka Domain Conditional Pointwise Mutual Information, PMI_DC… A zero-shot and few-shot multiple-choice scoring method for generative language models that compensates for surface form competition—the rat…	Curated	Evaluation Methods	`AIMech:PMIDCDomainConditionalPointwiseMutualInformation`	4 claims 3 sources
Domain-Adapted LLM aka Domain-Adapted Large Language Model, domain robustness… A large language model which is pre-trained on a broad corpus and then fine-tuned on domain-specific data to specialize its capabilities for…	AIO	Model	`AIO:DomainAdaptedLLM`	Imported
DoReFa-Net (Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients) aka DoReFa-Net, DoReFa-Net Low-Bitwidth Gradient Quantization… DoReFa-Net (Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients) is a low-bitwidth neural network training and i…	Curated	Algorithms	`AIMech:DoReFaNetTrainingLowBitwidthConvolutionalNeuralNetworksWithLowBitwidthGradients`	4 claims 3 sources
Dot Layer A layer that computes a dot product between samples in two tensors.	AIO	Layer	`AIO:DotLayer`	Imported
Double Greedy Algorithm for Unconstrained Non-Monotone Submodular Maximization aka Double Greedy Algorithm, Bidirectional Greedy Unconstrained Submodular Maximization… The Double Greedy algorithm is a single-pass linear-time algorithmic framework for Unconstrained Submodular Maximization (USM) of a non-nega…	Curated	Algorithms	`AIMech:DoubleGreedyUnconstrainedSubmodularMaximization`	3 claims 3 sources
DoubleSqueeze (Double-Pass Error-Compensated Gradient Compression) aka DoubleSqueeze, Double-Pass Error-Compensated Compression for Parallel SGD… A bidirectional communication-compressed parallel stochastic gradient descent algorithm (Tang et al. 2019, Algorithm 1) that applies error-c…	Curated	Algorithms	`AIMech:DoubleSqueezeDoublePassErrorCompensatedCompression`	4 claims 3 sources
Doubling slice sampling A univariate slice-sampling algorithm that expands a randomly placed initial interval by randomly directed doublings and uses shrinkage with…	Curated	Algorithms	`AIMech:DoublingSliceSampling`	1 claim 1 source
DRACO Byzantine-Resilient Distributed Training via Redundant Gradients aka DRACO, DRACO Coded Gradient Aggregation… A coding-theoretic Byzantine-resilient distributed optimization framework determined by an allocation matrix A, local node encoding function…	Curated	Algorithms	`AIMech:DracoByzantineResilientDistributedTrainingViaRedundantGradients`	3 claims 3 sources
DRAGON (Diverse Augmentation for Generalizable Dense Retrieval) aka Dense Retriever Trained with Diverse Augmentation, DRAGON Progressive Label Augmentation… A contrastive training algorithm for generalizable bi-encoder dense retrieval that combines large-scale diverse query augmentation (mixing c…	Curated	Algorithms	`AIMech:DRAGONDiverseAugmentationGeneralizableDenseRetrieval`	3 claims 3 sources
DropBlock A training-time feature-map transformation for convolutional networks that suppresses randomly placed contiguous spatial blocks of activatio…	Curated	Layers & Modules	`AIMech:DropBlock`	1 claim 2 sources
DropConnect A stochastic neural-network layer that masks individual weights and biases during training, so each example is processed through a randomly…	Curated	Layers & Modules	`AIMech:DropConnect`	1 claim 1 source
Dropout Boosting A dropout-mask training procedure proposed to optimize the likelihood of a normalized geometric ensemble, updating through a selected shared…	Curated	Algorithms	`AIMech:DropoutBoosting`	5 claims 1 source
Dropout Layer A regularization layer that applies Dropout to the input	AIO	Layer	`AIO:DropoutLayer`	Imported
DSGSUM Document-Level Semantic Graph Abstractive Summarization aka DSGSUM, Document-Level Semantic Graph Abstractive Summarization… A hybrid extractive-abstractive neural text summarization architecture that represents a source document as a sentence-level semantic graph…	Curated	Architectures	`AIMech:DSGSUMDocumentLevelSemanticGraphAbstractiveSummarization`	4 claims 3 sources
DSGT and GSGT (Distributed and Gossip Stochastic Gradient Tracking) aka DSGT and GSGT, Distributed Stochastic Gradient Tracking… A family of decentralized stochastic optimization algorithms over doubly stochastic network graphs W (Pu & Nedic 2021, Sections 2 and 4, Equ…	Curated	Algorithms	`AIMech:DsgtAndGsgtDistributedStochasticGradientTracking`	4 claims 3 sources
DUAL* The source’s MAX-rooted application of the dual of SSS*, using LIVE/SOLVED node descriptors, maximum-based merit updates and dual MAX/MIN ex…	Curated	Algorithms	`AIMech:DUALStar`	6 claims 1 source
Dual-averaging step-size adaptation for Hamiltonian samplers A warmup procedure that tunes the logarithm of a Hamiltonian sampler’s integration step size using cumulative discrepancy from a target acce…	Curated	Algorithms	`AIMech:DualAveragingHamiltonianStepSize`	1 claim 1 source
Dunning-Kruger Effect Bias aka Dunning-Kruger Effect A cognitive bias in which people with low ability in an area overestimate that ability. Often measured by comparing self-assessment with obj…	AIO	Bias	`AIO:DunningKrugerEffectBias`	Imported
Dutch eligibility traces An eligibility-trace update that propagates prior feature credit and adds a current-feature contribution adjusted by the prior trace’s proje…	Curated	Mathematical Methods	`AIMech:DutchEligibilityTraces`	5 claims 3 sources
DyLoRA (Dynamic Search-Free Low-Rank Adaptation) aka DyLoRA, Dynamic Low-Rank Adaptation… A dynamic, search-free parameter-efficient low-rank adaptation algorithm for pre-trained models that orders the information content of low-r…	Curated	Algorithms	`AIMech:DyLoRADynamicSearchFreeLowRankAdaptation`	5 claims 3 sources
DynaBERT: Dynamic BERT with Adaptive Width and Depth aka DynaBERT, DynaBERT Adaptive Width and Depth Transformer… A dynamic Transformer architecture and two-stage distillation training method that adapts a task-specific BERT or RoBERTa model across both…	Curated	Architectures	`AIMech:DynaBERTDynamicBERTWithAdaptiveWidthAndDepth`	4 claims 3 sources
Dynamic Conditional Correlation aka DCC A model that allows for time-varying correlations between different time series, used in financial econometrics to model and forecast covari…	AIO	Model	`AIO:DynamicConditionalCorrelation`	Imported
Dynamic Convolutional Layer aka Dynamic Convolution Layer A neural layer that convolves feature maps with filters generated from the current input by a learned subnetwork, allowing the applied kerne…	Curated	Layers & Modules	`AIMech:DynamicConvolutionalLayer`	6 claims 1 source
Dynamic Memory Network aka DMN, Dynamic Memory Networks A recurrent neural architecture that encodes an input and a question, repeatedly forms question-conditioned episodes from input facts to upd…	Curated	Architectures	`AIMech:DynamicMemoryNetwork`	6 claims 1 source
Dynamic Memory Network Plus aka DMN+ A recurrent question-answering architecture that fuses text or image facts, aggregates them with question- and memory-conditioned attention…	Curated	Architectures	`AIMech:DynamicMemoryNetworkPlus`	6 claims 1 source
Dynamic topic model aka DTM A time-sliced topic-model family that links the softmax natural parameters of corresponding topic-word distributions across slices through G…	Curated	Model Families	`AIMech:DynamicTopicModel`	2 claims 1 source
E-detector nonparametric sequential change detection aka E-Detector, P-e-detector… A nonparametric, nonasymptotic sequential changepoint detection framework (Shin, Ramdas, & Rinaldo 2024) defined with respect to a composite…	Curated	Mathematical Methods	`AIMech:EDetectorSequentialChangeDetection`	4 claims 3 sources
E-value Benjamini-Hochberg procedure aka e-BH Procedure, Base e-BH and Boosted e-BH Multiple Testing Procedure… A step-down multiple hypothesis testing procedure (Wang & Ramdas 2022) for controlling the false discovery rate (FDR) at target level alpha…	Curated	Mathematical Methods	`AIMech:EValueBenjaminiHochbergProcedure`	4 claims 2 sources
E-value calibration and merging aka E-Value Calibration and Combination Framework, Vovk-Wang E-Merging and P-to-E Calibration… A statistical hypothesis testing and evidence synthesis framework (Vovk & Wang 2021) based on e-variables—nonnegative random variables E >=…	Curated	Mathematical Methods	`AIMech:EValueCalibrationAndMerging`	4 claims 2 sources
Early Dropout A neural-network training procedure that applies dropout during an initial portion of optimization and disables it for the remaining trainin…	Curated	Algorithms	`AIMech:EarlyDropout`	5 claims 1 source
Echo State Network aka ESN A recurrent neural network with a recurrent hidden layer and sparsely connected hidden neurons that learns output weights to produce tempora…	AIO	Network	`AIO:EchoStateNetwork`	Imported
Eclat Frequent-itemset mining using depth-first enumeration and transaction-set intersections.	Curated	Algorithms	`AIMech:Eclat`	1 claim 1 source
Ecological Fallacy Bias aka Ecological Fallacy A selection and sampling bias occurring when an inference about an individual is made based on their group membership.	AIO	Bias	`AIO:EcologicalFallacyBias`	Imported
Edge-Popup Untrained Subnetwork Score Optimization aka Edge-Popup, edge-popup Algorithm… A subnetwork discovery algorithm for randomly weighted neural networks that keeps all weights w_{uv} (including first, last, and batch-norma…	Curated	Algorithms	`AIMech:EdgePopupUntrainedSubnetworkScoreOptimization`	4 claims 3 sources
EF-BV Unified Error Feedback and Variance Reduction with Bias-Variance Decomposition aka EF-BV, Error Feedback with Bias-Variance Decomposition… A unified distributed compressed proximal gradient algorithm (Algorithm 1) operating over the two-parameter bias-variance compressor class C…	Curated	Algorithms	`AIMech:EfBvUnifiedErrorFeedbackAndVarianceReductionWithBiasVarianceDecomposition`	4 claims 3 sources
EF21 Algorithmic Extensions (EF21-SGD, EF21-PAGE, EF21-PP, EF21-BC, EF21-HB, EF21-Prox) aka EF21 with Bells and Whistles, EF21-PAGE… A suite of six algorithmic extensions of the Markov-compressor error-feedback method EF21 for distributed nonconvex and Polyak-Lojasiewicz (…	Curated	Algorithms	`AIMech:Ef21ExtensionsStochasticVarianceReducedPartialParticipationBidirectionalAndProximalErrorFeedback`	4 claims 3 sources
EF21 Markov-Compressor Error Feedback for Heterogeneous Nonconvex Distributed Optimization aka EF21, Error Feedback 2021… A communication-compressed distributed optimization algorithm (EF21) in which each worker i in [n] maintains a local gradient estimator g_i^…	Curated	Algorithms	`AIMech:Ef21MarkovCompressorErrorFeedbackForHeterogeneousNonconvexOptimization`	4 claims 3 sources
Efficient Global Optimization The original sequential optimization algorithm of Jones, Schonlau and Welch for expensive deterministic scalar functions on bounded continuo…	Curated	Algorithms	`AIMech:EfficientGlobalOptimization`	6 claims 1 source
EKFAC (Eigenvalue-Corrected Kronecker Factorization) aka EKFAC, EKFAC-ra… An approximate natural gradient optimization and Fisher information matrix factorization method that projects layer-wise parameter gradients…	Curated	Algorithms	`AIMech:EKFACEigenvalueCorrectedKroneckerFactorizationNaturalGradient`	5 claims 3 sources
Elastic net aka Elastic-net regression Linear regression regularized by a combination of L1 and L2 penalties.	Curated	Mathematical Methods	`AIMech:ElasticNet`	1 claim 1 source
Election Coding for Byzantine-Robust SignSGD with Majority Vote aka Election Coding, Election-Coded SignSGD-MV… A coding-theoretic hierarchical majority-voting framework proposed by Sohn, Han, Choi, and Moon (NeurIPS 2020) that protects 1-bit compresse…	Curated	Algorithms	`AIMech:ElectionCodingForByzantineRobustSignSgd`	4 claims 3 sources
Elitist Ant System aka ASelite An Ant System variant that retains the standard all-ant pheromone deposits and adds extra reinforcement to edges of the best-so-far tour aft…	Curated	Algorithms	`AIMech:ElitistAntSystem`	1 claim 2 sources
Elliptical slice sampling aka ESS A Markov-chain update for a target factored into a Gaussian prior and a likelihood, which performs an angular slice search along the ellipse…	Curated	Algorithms	`AIMech:EllipticalSliceSampling`	1 claim 1 source
ELU Function aka ELU, Exponential Linear Unit A mathematical function that is x if x > 0 and alpha * (exp(x) - 1) if x < 0 where alpha controls the value to which an ELU saturates for ne…	AIO	MathematicalFunction	`AIO:ELUFunction`	Imported
ELU Layer An activation layer that applies the Exponential Linear Unit (ELU) function element-wise.	AIO	Layer	`AIO:ELULayer`	Imported
Embedding Layer A layer that turns positive integers (indexes) into dense vectors of fixed size.	AIO	Layer	`AIO:EmbeddingLayer`	Imported
Embodied LLM aka Embodied Large Language Model, multimodal grounding A large language model that integrates language with other modalities like vision audio and robotics to enable grounded language understandi…	AIO	Model	`AIO:EmbodiedLLM`	Imported
Emergent Bias A use and interpretation bias resulting from the use and reliance on algorithms across new or unanticipated contexts.	AIO	Bias	`AIO:EmergentBias`	Imported
Encoder LLM A large language model that uses an encoder-only architecture to encode the input sequence into a fixed-length representation which is then…	AIO	Model	`AIO:EncoderLLM`	Imported
Encoder-Decoder LLM A large language model introduced in the "Attention Is All You Need" paper. The encoder processes the input sequence to generate a hidden re…	AIO	Model	`AIO:EncoderDecoderLLM`	Imported
End-to-End Memory Network aka MemN2N, End-to-End Memory Networks A neural architecture that answers a query through one or more differentiable soft-attention reads over separately embedded input and output…	Curated	Architectures	`AIMech:EndToEndMemoryNetwork`	6 claims 1 source
Energy-Based LLM aka Energy-Based Large Language Model, energy scoring… A large language model which models the explicit probability density over token sequences using an energy function, rather than an autoregre…	AIO	Model	`AIO:EnergyBasedLLM`	Imported
Enforced hill climbing A forward state-space search controller that repeatedly uses breadth-first search to find a state with a strictly smaller heuristic value, c…	Curated	Algorithms	`AIMech:EnforcedHillClimbing`	5 claims 1 source
Ensemble Learning A machine learning task focused on methods that use multiple learning algorithms to achieve better predictive performance than any of the co…	AIO	MachineLearningTask	`AIO:EnsembleLearning`	Imported
Entangled Polynomial Codes for Straggler-Resilient Distributed Matrix Multiplication aka Entangled Polynomial Code, Entangled Polynomial Codes… A straggler-resilient linear coded computing method for distributed matrix multiplication C = A^T B across N worker nodes that partitions A…	Curated	Algorithms	`AIMech:EntangledPolynomialCodesForStragglerResilientDistributedMatrixMultiplication`	3 claims 3 sources
Entropic Gromov-Wasserstein Discrepancy and Barycenter Averaging aka Entropic Gromov-Wasserstein Distance and Barycenter, Gromov-Wasserstein Kernel and Distance Matrix Averaging… Entropic Gromov-Wasserstein Discrepancy and Barycenter Averaging is a metric-measure alignment and relational matrix averaging methodology i…	Curated	Algorithms	`AIMech:EntropicGromovWassersteinDiscrepancyAndBarycenterAveraging`	3 claims 3 sources
Entropy Search A Bayesian global optimization algorithm that approximates the location of a function minimum on sampled representer points using expectatio…	Curated	Algorithms	`AIMech:EntropySearch`	6 claims 2 sources
Entrywise First-Order Eigenvector Approximation and Leave-One-Out Perturbation Analysis for Low-Expected-Rank Random Matrices aka Abbe-Fan-Wang-Zhong Entrywise Eigenvector Analysis, First-Order Entrywise Eigenvector Approximation via Leave-One-Out Perturbation… A probabilistic entrywise ($\ell_\infty$ and $2 \to \infty$ norm) eigenvector and eigenspace perturbation framework for symmetric random mat…	Curated	Mathematical Methods	`AIMech:EntrywiseFirstOrderEigenvectorApproximationAndLeaveOneOutPerturbationAnalysisForLowExpectedRankRandomMatrices`	3 claims 3 sources
EPIC Expansion via Prediction of Importance with Contextualization aka EPIC, Expansion via Prediction of Importance with Contextualization… A lexicon-grounded representation-based neural passage re-ranking architecture that maps a query q into a sparse \|V\|-dimensional vector phi_…	Curated	Architectures	`AIMech:EPICExpansionViaPredictionOfImportanceWithContextualization`	4 claims 3 sources
Eppstein–Wang RAND closeness approximation aka Eppstein-Wang closeness approximation A randomized graph-analysis algorithm that estimates closeness centrality from independent uniformly sampled source vertices, averaging scal…	Curated	Algorithms	`AIMech:EppsteinWangRANDClosenessApproximation`	6 claims 1 source
EPR Efficient Prompt Retrieval for In-Context Learning aka EPR, Efficient Prompt Retrieval… A supervised dense prompt retrieval method for in-context learning that first filters candidate training demonstrations for each training ex…	Curated	Algorithms	`AIMech:EPREfficientPromptRetrievalForInContextLearning`	4 claims 3 sources
Epsilon-truncation for Conditional Distribution Prediction aka CDP epsilon-truncation A modification of conditional distribution prediction for IDA* tree size that removes conditional child-type probabilities below a calibrate…	Curated	Algorithms	`AIMech:EpsilonTruncationCDP`	5 claims 1 source
Equal opportunity in binary classification aka Equal opportunity (true-positive parity), Equality of opportunity (true-positive parity) A binary-classification fairness criterion requiring equal probabilities of a positive prediction across specified protected groups among in…	Curated	Evaluation Criteria	`AIMech:EqualOpportunity`	1 claim 1 source
Equalized odds aka Equalised odds A fairness criterion requiring a predictor's output to be conditionally independent of a specified protected attribute given the target outc…	Curated	Evaluation Criteria	`AIMech:EqualizedOdds`	1 claim 1 source
Equalized-odds postprocessing for binary predictors aka Hardt equalized-odds binary postprocessing A randomized postprocessing algorithm that uses a binary predictor and protected-group membership to minimize expected label loss subject to…	Curated	Algorithms	`AIMech:EqualizedOddsBinaryPostprocessing`	1 claim 1 source
Error Propagation Bias aka Error Propagation A processing bias characterized by the effect of variables' uncertainties (or errors more specifically random errors) on the uncertainty of…	AIO	Bias	`AIO:ErrorPropagationBias`	Imported
Escape-Through-a-Mesh Null-Space Phase Transition Thresholds for Nuclear Norm and PSD Trace Minimization aka Oymak-Hassibi Nuclear Norm Recovery Thresholds, Escape-Through-a-Mesh Matrix Rank Minimization Thresholds… A high-dimensional random-matrix and Grassmannian escape-through-a-mesh phase-transition methodology (introduced by Samet Oymak and Babak Ha…	Curated	Mathematical Methods	`AIMech:EscapeThroughAMeshNullSpacePhaseTransitionThresholdsForNuclearNormAndPSDTraceMinimization`	3 claims 2 sources
Estimation of distribution algorithms A family of population-based optimization algorithms whose central offspring-generation mechanism estimates a search distribution from selec…	Curated	Algorithms	`AIMech:EstimationOfDistributionAlgorithms`	6 claims 3 sources
Ethical LLM aka Ethical Large Language Model, constituitional AI… A large language model that is trained to uphold certain ethical principles values or rules in its language generation to increase safety an…	AIO	Model	`AIO:EthicalLLM`	Imported
Evaluation Bias A selection and sampling bias arising when testing populations do not equally represent user populations or when inappropriate performance m…	AIO	Bias	`AIO:EvaluationBias`	Imported
Evolutionary LLM aka Evolutionary Language Model, evolutionary algorithms… A large language model that applies principles of evolutionary computation to optimize its structure and parameters evolving over time to im…	AIO	Model	`AIO:EvolutionaryLLM`	Imported
Exact Diffusion (Adapt-Correct-Combine Distributed Optimization) aka Exact Diffusion, Adapt-Correct-Combine Exact Diffusion… A bias-corrected distributed optimization algorithm over locally balanced left-stochastic combination matrices A (A^T 1 = 1, A p = p, P A^T…	Curated	Algorithms	`AIMech:ExactDiffusionAdaptCorrectCombineDistributedOptimization`	4 claims 3 sources
Exact harmonic mean p-value combination test aka EHMP, Exact Harmonic Mean P-Value Test A statistical p-value combination method that aggregates m hypothesis test p-values p_1, ..., p_m in (0, 1] with non-negative weights w_1, .…	Curated	Mathematical Methods	`AIMech:ExactHarmonicMeanPValueTest`	4 claims 1 source
Exact PoClustering aka Maximal-clique PoClustering A dissimilarity-based clustering construction that accumulates maximal cliques of pairwise-distance threshold graphs and organizes their set…	Curated	Algorithms	`AIMech:ExactPoClustering`	6 claims 2 sources
exact step-up and step-down false discovery proportion moment formulas and least favorable configuration analysis aka Roquain-Villers Exact Step-Up and Step-Down FDP Distribution and Moment Framework, Conditional Binomial Step-Up FDP Law and Stirling-Number Moment Decomposition… A finite-sample multiple hypothesis testing analysis framework developed by Etienne Roquain and Fanny Villers (2011, Annals of Statistics 39…	Curated	Mathematical Methods	`AIMech:ExactStepUpStepDownFDPMomentsAndLFCAnalysis`	4 claims 4 sources
exchangeable largest crossing point asymptotic false discovery rate and global-null independence limit discontinuity aka Finner-Dickhaus-Roters Exchangeable LCP Asymptotic FDR Framework, Dirac-Exchangeable Conditional Empirical CDF Largest Crossing Point (LCP) Method… An asymptotic multiple hypothesis testing analysis framework introduced by Helmut Finner, Thorsten Dickhaus, and Markus Roters (2007, Annals…	Curated	Mathematical Methods	`AIMech:ExchangeableLCPAsymptoticFDRAndIndependenceLimit`	4 claims 3 sources
Exclusion Bias A selection and sampling bias occurring when specific groups of user populations are excluded from testing and analysis.	AIO	Bias	`AIO:ExclusionBias`	Imported
Exemplar-Based Convex Clustering aka Convex Clustering with Exemplar-Based Models, Convex Mixture Model Clustering An exemplar-based clustering procedure that fixes candidate component centers at every observed point, fits their simplex weights through a…	Curated	Algorithms	`AIMech:ExemplarBasedConvexClustering`	5 claims 1 source
Expando-Mono-Duo: Multi-Stage Text Ranking with Pretrained Sequence-to-Sequence Models aka Expando-Mono-Duo T5 Multi-Stage Ranking Architecture, DuoT5 Pairwise Sequence-to-Sequence Reranker… A four-stage retrieve-and-rerank architecture (Pradeep, Nogueira, & Lin, 2021) built on pretrained sequence-to-sequence Transformers (T5) th…	Curated	Architectures	`AIMech:ExpandoMonoDuoT5MultiStageDocumentRanking`	3 claims 3 sources
Expectation Conditional Maximization aka ECM Algorithm, ECM An extension of expectation maximization that replaces a joint maximization of the expected complete-data log likelihood with a sequence of…	Curated	Algorithms	`AIMech:ExpectationConditionalMaximization`	3 claims 1 source
Expectation Conditional Maximization Either aka ECME Algorithm, ECME An extension of expectation conditional maximization that replaces selected final conditional maximizations of expected complete-data log li…	Curated	Algorithms	`AIMech:ExpectationConditionalMaximizationEither`	3 claims 2 sources
Expectation maximization aka EM Parameter estimation alternating expected complete-data log-likelihood evaluation and its maximization.	Curated	Algorithms	`AIMech:ExpectationMaximization`	1 claim 1 source
Expected improvement acquisition An acquisition criterion for deterministic scalar minimization that scores a candidate evaluation by the predictive expected positive reduct…	Curated	Mathematical Methods	`AIMech:ExpectedImprovementAcquisition`	5 claims 1 source
Explainable LLM aka Explainable Language Model, XAI LLM… A large language model that is designed to provide insights into its decision-making process making it easier for users to understand and tr…	AIO	Model	`AIO:ExplainableLLM`	Imported
Exponential Function A mathematical function denoted by f(x)=exp or e^{x}.	AIO	MathematicalFunction	`AIO:ExponentialFunction`	Imported
Exponential generalized root model aka Exponential GRM A generalized root probability model on nonnegative continuous variables with exponential base measure and symmetric root-product interactio…	Curated	Model Families	`AIMech:ExponentialGeneralizedRootModel`	1 claim 1 source
Exponential natural evolution strategies A Gaussian black-box optimization algorithm that adapts a search mean and full covariance factor from ranked samples in local standard-norma…	Curated	Algorithms	`AIMech:ExponentialNaturalEvolutionStrategies`	6 claims 1 source
Exponential Smoothing State Space Model aka ETS A model that combines exponential smoothing with state space modeling, allowing for the inclusion of both trend and seasonal components. Use…	AIO	Model	`AIO:ExponentialSmoothingStateSpaceModel`	Imported
Exponential square root graphical model aka Exponential SQR, Exponential square root Markov random field A graphical probability model on nonnegative continuous variables with unary square-root terms and symmetric products of square roots, deriv…	Curated	Model Families	`AIMech:ExponentialSquareRootGraphicalModel`	1 claim 2 sources
Exponential-family harmonium aka EFH A bipartite undirected model family coupling visible and hidden exponential-family sufficient statistics through bilinear interactions, with…	Curated	Model Families	`AIMech:ExponentialFamilyHarmonium`	3 claims 1 source
Exponentiated-gradient reduction for fair classification aka Agarwal exponentiated-gradient fairness reduction A cost-sensitive classification reduction that alternates classifier best responses with exponentiated-gradient updates of bounded Lagrange…	Curated	Algorithms	`AIMech:ExponentiatedGradientFairClassification`	1 claim 1 source
Extended Guided Local Search aka EGLS The Tsang–Mills–Ford extension of Guided Local Search that combines cost-scaled penalty weighting, aspiration for a new best original-object…	Curated	Algorithms	`AIMech:ExtendedGuidedLocalSearch`	1 claim 1 source
EXTRA (Exact First-Order Algorithm for Decentralized Consensus Optimization) aka EXTRA Decentralized Consensus Optimization, Exact First-Order Algorithm for Decentralized Consensus Optimization… An exact first-order decentralized consensus optimization algorithm for minimizing bar_f(x) = (1/n) sum_{i=1}^n f_i(x) over an undirected co…	Curated	Algorithms	`AIMech:ExtraExactFirstOrderDecentralizedConsensusOptimization`	4 claims 3 sources
Extreme Learning Machine aka ELM A feedback network with randomly assigned hidden nodes that are not updated during training.	AIO	Network	`AIO:ExtremeLearningMachine`	Imported
F-Race A statistical racing method for configuring metaheuristics that evaluates a finite candidate set on shared problem-instance blocks and elimi…	Curated	Algorithms	`AIMech:FRace`	1 claim 1 source
FABOLAS aka Fast Bayesian Optimization on Large Data Sets A Bayesian hyperparameter optimization algorithm that jointly chooses a model configuration and training-data subset size using surrogate mo…	Curated	Algorithms	`AIMech:FABOLAS`	2 claims 5 sources
Factor-Adjusted Regularized Model Selection and Decorrelated Variable Screening aka FarmSelect, Factor-Adjusted Regularized Model Selection… A two-step high-dimensional model-selection and variable-screening methodology (introduced by Jianqing Fan, Yuan Ke, and Kaizheng Wang in 20…	Curated	Algorithms	`AIMech:FactorAdjustedRegularizedModelSelectionAndDecorrelatedVariableScreening`	3 claims 3 sources
Factored Language Model aka Factorized Language Model A language model that views each word as a vector of multiple factors such as part-of-speech morphology and semantics to improve language mo…	AIO	Model	`AIO:FactoredLanguageModel`	Imported
Factored restricted Boltzmann machine language model aka FRBM A conditional neural word model that factorizes position-specific word-to-hidden weights through a shared word-embedding matrix and couples…	Curated	Architectures	`AIMech:FactoredRestrictedBoltzmannMachineLanguageModel`	1 claim 1 source
Factorial hidden Markov model aka FHMM, Factorial HMM A directed latent sequence-model family in which several independently evolving hidden Markov chains jointly determine the observation distr…	Curated	Model Families	`AIMech:FactorialHiddenMarkovModel`	1 claim 1 source
Factorized LHUC Adaptation An acoustic-model adaptation procedure that combines separately estimated speaker and environment LHUC transforms by interpolating their tra…	Curated	Algorithms	`AIMech:FactorizedLHUCAdaptation`	5 claims 1 source
Factorized LLM aka Factorized Large Language Model, Factorized Learning Assisted with Large Language Model… A large language model that decomposes the full language modeling task into multiple sub-components or experts that each focus on a subset o…	AIO	Model	`AIO:FactorizedLLM`	Imported
Factorized variational sparse-spectrum Gaussian-process inference aka fVSSGP The Gal–Turner finite spectral regression inference procedure that explicitly optimizes diagonal Gaussian output-coefficient factors and ind…	Curated	Algorithms	`AIMech:FactorizedVariationalSparseSpectrumGaussianProcessInference`	5 claims 3 sources
FADA (Federated Adversarial Domain Adaptation) aka FADA, Federated Adversarial Domain Adaptation FADA (Federated Adversarial Domain Adaptation) is a privacy-preserving multi-source unsupervised domain adaptation algorithm for federated l…	Curated	Algorithms	`AIMech:FadaFederatedAdversarialDomainAdaptation`	4 claims 3 sources
FAIRLEARNING aka Kusner counterfactual fair learning A causal-model-dependent learning procedure that minimizes predictive loss averaged over inferred background variables, restricting the late…	Curated	Algorithms	`AIMech:FairLearning`	1 claim 1 source
Fairness LP aka Dwork fairness linear program A finite-population optimization procedure that assigns outcome distributions to individuals to minimize expected loss under pairwise Lipsch…	Curated	Algorithms	`AIMech:FairnessLP`	1 claim 1 source
Family-of-harmonium aka FoH A classification model family comprising separately parameterized harmoniums for each class, with binary text features and Gaussian image fe…	Curated	Model Families	`AIMech:FamilyOfHarmonium`	3 claims 1 source
Fast AutoAugment aka FAA An augmentation-policy search procedure that evaluates candidate transformations on held-out training examples using a fixed classifier trai…	Curated	Algorithms	`AIMech:FastAutoAugment`	2 claims 5 sources
Fast condensed prototype-based domain description aka FastCPDD, FCPDD A heuristic for selecting PDD prototypes that samples remaining reference observations, computes their radius offsets against the full datas…	Curated	Algorithms	`AIMech:FastCondensedPrototypeBasedDomainDescription`	5 claims 1 source
Fast Dropout Training aka Fast dropout A dropout approximation procedure that replaces masked weighted sums by Gaussian distributions with matched means and variances, using Gauss…	Curated	Algorithms	`AIMech:FastDropoutTraining`	5 claims 2 sources
Fast Global Kernel K-Means An incremental kernel clustering algorithm that chooses each new singleton seed by maximizing a computable lower bound on error reduction, t…	Curated	Algorithms	`AIMech:FastGlobalKernelKMeans`	4 claims 1 source
Fast Local Search aka FLS A neighborhood-search procedure that uses activation bits to scan selected subneighborhoods, deactivating unsuccessful ones and reactivating…	Curated	Algorithms	`AIMech:FastLocalSearch`	1 claim 2 sources
Fast persistent contrastive divergence aka FPCD A persistent-chain RBM learning algorithm that adds rapidly updated, rapidly decaying auxiliary parameters to the sampling energy while reta…	Curated	Algorithms	`AIMech:FastPersistentContrastiveDivergence`	1 claim 1 source
Fast Wasserstein Barycenters and Smoothed Dual Subgradient Descent aka Entropic Smoothed Wasserstein Barycenter Optimization, Cuturi-Doucet Fast Wasserstein Barycenter Algorithm… Fast Wasserstein Barycenters and Smoothed Dual Subgradient Descent is a computational optimal transport framework introduced by Cuturi and D…	Curated	Algorithms	`AIMech:FastWassersteinBarycentersAndSmoothedDualSubgradientDescent`	3 claims 3 sources
FastBERT: Self-Distilling BERT with Adaptive Inference Time aka FastBERT, FastBERT Self-Distilling Adaptive-Inference Transformer… A sample-wise adaptive Transformer architecture and three-stage training paradigm that appends a teacher classifier to the final layer L-1 a…	Curated	Architectures	`AIMech:FastBERTSelfDistillingBERTWithAdaptiveInferenceTime`	4 claims 3 sources
Faster Least Squares Approximation via Randomized Hadamard Preconditioning aka DMMS Faster Least Squares Approximation, Randomized Hadamard Preconditioned Sketch-and-Solve Least Squares… Faster Least Squares Approximation via Randomized Hadamard Preconditioning is a randomized sketch-and-solve algorithm for overconstrained l_…	Curated	Algorithms	`AIMech:FasterLeastSquaresApproximationViaRandomizedHadamardPreconditioning`	3 claims 3 sources
FastICA aka Fast Independent Component Analysis A family of independent-component estimation algorithms that repeatedly apply normalized approximate-Newton fixed-point updates to nonlinear…	Curated	Algorithms	`AIMech:FastICA`	4 claims 2 sources
Feature Extraction aka Attribute Extraction, Feature Isolation… A data enhancement that transforms raw data into a set of measurable characteristics that can be used as input for machine learning algorith…	AIO	Preprocessing	`AIO:FeatureExtraction`	Imported
Feature-wise Linear Modulation aka FiLM A neural conditioning layer that applies a feature-wise affine transformation whose scale and shift are generated from conditioning informat…	Curated	Layers & Modules	`AIMech:FeatureWiseLinearModulation`	5 claims 1 source
Fed-ET (Heterogeneous Ensemble Knowledge Transfer with Confidence-Weighted Consensus and Diversity Regularization) aka Fed-ET, Federated Ensemble Knowledge Transfer… A bi-directional ensemble knowledge transfer framework for model-heterogeneous federated learning (Cho, Manoel, Joshi, Sim, & Dimitriadis 20…	Curated	Algorithms	`AIMech:FedEtHeterogeneousEnsembleKnowledgeTransferWithWeightedConsensusAndDiversityRegularization`	4 claims 3 sources
Fed-RoD (Federated Robust Decoupling for Generic and Personalized Learning) aka Fed-RoD, Fed-RoD with Balanced Softmax Risk Management… A dual-objective federated classification framework (Chen & Chao 2022, Section 4, Equations 6-9, Theorem 1) that simultaneously trains a cla…	Curated	Algorithms	`AIMech:FedRodFederatedRobustDecouplingForGenericAndPersonalizedLearning`	4 claims 3 sources
FedALA (Adaptive Local Aggregation for Personalized Federated Learning) aka FedALA, Federated Learning with Adaptive Local Aggregation… A personalized federated learning algorithm (Zhang et al. 2023, Section 3, Equations 1-6, Algorithm 1) whose Adaptive Local Aggregation (ALA…	Curated	Algorithms	`AIMech:FedAlaAdaptiveLocalAggregationForPersonalizedFederatedLearning`	4 claims 3 sources
FedAlign (Data-Free Final-Block Lipschitz Self-Distillation via Slimmed Sub-Block Transmitting Matrices) aka FedAlign, Federated Final-Block Lipschitz Alignment… A resource-efficient local self-distillation regularization algorithm for heterogeneous federated learning (Mendieta, Yang, Wang, Lee, Ding,…	Curated	Algorithms	`AIMech:FedAlignFinalBlockLipschitzSelfDistillationForHeterogeneousFederatedLearning`	4 claims 3 sources
FedAMP (Federated Attentive Message Passing for Personalized Cross-Silo Federated Learning) aka FedAMP, HeurFedAMP… A personalized cross-silo federated learning algorithm (Huang et al. 2021, Sections 3-6, Definition 1, Equations 1-8, Algorithm 1, Theorems…	Curated	Algorithms	`AIMech:FedAmpFederatedAttentiveMessagePassingForPersonalizedCrossSiloFederatedLearning`	4 claims 3 sources
FedAUX (Certainty-Weighted Unsupervised Auxiliary Ensemble Distillation for Federated Learning) aka FedAUX, Federated Auxiliary Data Distillation… An unlabeled-auxiliary-data federated learning and ensemble distillation framework (Sattler, Korjakow, Rischke, & Samek 2021, Sections 3.2-3…	Curated	Algorithms	`AIMech:FedAuxCertaintyWeightedUnsupervisedAuxiliaryEnsembleDistillationForFederatedLearning`	4 claims 3 sources
FedAwS (Federated Averaging with Spreadout for Positive-Only Labels) aka FedAwS, Federated Averaging with Spreadout A federated multi-class and extreme-classification training algorithm (Yu, Rawat, Menon, & Kumar 2020, Section 3, Equations 7-8, Algorithm 1…	Curated	Algorithms	`AIMech:FedAwsFederatedAveragingWithSpreadoutForPositiveOnlyLabels`	4 claims 3 sources
FedBABU (Federated Averaging with Body Aggregation and Body Update) aka FedBABU, Federated Averaging with Body Aggregation and Body Update… A decoupled representation-learning federated optimization algorithm (Oh, Kim, & Yun 2022, Section 5, Algorithms 1-2) that decomposes the de…	Curated	Algorithms	`AIMech:FedBabuFederatedAveragingWithBodyAggregationAndBodyUpdate`	4 claims 3 sources
FedBE (Federated Bayesian Model Ensemble via Stochastic Weight Average Distillation) aka FedBE, Federated Bayesian Ensemble… A Bayesian server-side model aggregation algorithm for multi-round federated learning (Chen & Chao 2021, Sections 3-4, Equations 3-9, Algori…	Curated	Algorithms	`AIMech:FedBeFederatedBayesianModelEnsembleViaStochasticWeightAverageDistillation`	4 claims 3 sources
FedBN (Federated Learning on Non-IID Features via Local Batch Normalization) aka FedBN, Federated Learning with Local Batch Normalization… A federated learning aggregation modality (FedBN, Algorithm 1) designed for feature-shift non-IID data (covariate shift where marginal input…	Curated	Algorithms	`AIMech:FedBnFederatedLearningOnNonIidFeaturesViaLocalBatchNormalization`	4 claims 3 sources
FedBuff (Federated Learning with Buffered Asynchronous Aggregation) aka FedBuff, Buffered Asynchronous Federated Aggregation… A buffered asynchronous federated optimization algorithm (Nguyen et al. 2022, Section 3, Algorithm 1) in which the server schedules up to M…	Curated	Algorithms	`AIMech:FedBuffBufferedAsynchronousFederatedAggregation`	4 claims 3 sources
FedCorr (Multi-Stage Federated Learning for Heterogeneous Label Noise Correction) aka FedCorr, Multi-Stage Federated Learning for Label Noise Correction… A three-stage federated learning framework for heterogeneous client label noise (Xu et al. 2022, Section 3, Equations 1-7, Algorithm 1) that…	Curated	Algorithms	`AIMech:FedCorrMultiStageLabelNoiseCorrectionForFederatedLearning`	4 claims 3 sources
FedCP (Federated Conditional Policy for Sample-Wise Feature Information Separation) aka FedCP, Federated Conditional Policy… A personalized federated learning algorithm (Zhang et al. 2023, Section 3.2, Equations 2-8, Algorithm 1) that separates each input sample's…	Curated	Algorithms	`AIMech:FedCpConditionalPolicyFeatureSeparationForPersonalizedFederatedLearning`	4 claims 3 sources
FedCurv (Fisher-Information-Regularized Federated Learning for Non-IID Data) aka FedCurv, Fisher-Information-Regularized Federated Learning… A curvature-regularized federated learning algorithm (Shoham et al. 2019, Section 3, Equations 1-5) that mitigates catastrophic forgetting a…	Curated	Algorithms	`AIMech:FedCurvFisherInformationRegularizedFederatedLearning`	4 claims 3 sources
FedDC (Federated Learning via Local Drift Decoupling and Correction) aka FedDC, Federated Learning via Local Drift Decoupling and Correction… A primal-dual drift-decoupling and gradient-correction federated learning algorithm (Gao et al. 2022, Section 4, Equations 3-8, Appendix B A…	Curated	Algorithms	`AIMech:FedDcLocalDriftDecouplingAndCorrectionForNonIidFederatedLearning`	4 claims 3 sources
FedDecorr (Federated Feature Decorrelation Regularization for Mitigating Dimensional Collapse) aka FedDecorr, Federated Feature Decorrelation Regularization… A heterogeneous federated representation learning algorithm (Shi et al. 2023, Sections 3.3-4, Theorem 1, Proposition 1, Equations 6-9, Algor…	Curated	Algorithms	`AIMech:FedDecorrFeatureDecorrelationForDimensionalCollapseMitigationInFederatedLearning`	4 claims 3 sources
FedDF (Ensemble Distillation for Robust Model Fusion in Federated Learning) aka FedDF, Federated Distillation Fusion… A server-side ensemble distillation framework for federated model fusion (FedDF, Algorithm 1 for homogeneous models and Algorithm 3 for hete…	Curated	Algorithms	`AIMech:FedDfEnsembleDistillationForRobustModelFusionInFederatedLearning`	4 claims 3 sources
FedDG Episodic Learning in Continuous Frequency Space for Federated Domain Generalization aka FedDG, ELCFS… A federated domain generalization algorithm (Liu, Chen, Qin, Dou, & Heng, 2021) that learns a shared prediction model from K decentralized s…	Curated	Algorithms	`AIMech:FedDgEpisodicLearningInContinuousFrequencySpaceForFederatedDomainGeneralization`	4 claims 3 sources
FedDisco (Federated Learning with Discrepancy-Aware Collaboration) aka FedDisco, Federated Learning with Discrepancy-Aware Collaboration… A federated aggregation algorithm for category-imbalanced and non-IID client datasets (Ye et al. 2023, Sections 3.2-5.2, Proposition 4.1, Th…	Curated	Algorithms	`AIMech:FedDiscoFederatedLearningWithDiscrepancyAwareCollaboration`	4 claims 3 sources
FedDR and asyncFedDR (Randomized Douglas-Rachford Splitting for Nonconvex Federated Composite Optimization) aka FedDR, asyncFedDR… A family of synchronous (FedDR, Algorithm 1) and asynchronous (asyncFedDR, Algorithm 2) randomized block-coordinate Douglas-Rachford splitti…	Curated	Algorithms	`AIMech:FedDrAndAsyncFedDrRandomizedDouglasRachfordSplittingForNonconvexFederatedCompositeOptimization`	4 claims 3 sources
FedDyn Dynamic Regularization for Federated Learning aka FedDyn, Federated Learning Based on Dynamic Regularization… A communication-efficient federated optimization method (FedDyn) in which each active device k in P_t at round t minimizes a dynamically reg…	Curated	Algorithms	`AIMech:FedDynDynamicRegularizationForFederatedLearning`	4 claims 3 sources
FedEMA (Federated Divergence-Aware Exponential Moving Average Update for Self-Supervised Learning) aka FedEMA, Federated Divergence-aware Exponential Moving Average… A federated self-supervised representation learning algorithm (Zhuang, Wen, & Zhang 2022, Sections 3.2 & 4, Equations 1-3, Algorithm 1) buil…	Curated	Algorithms	`AIMech:FedEmaDivergenceAwareExponentialMovingAverageFederatedSelfSupervisedLearning`	4 claims 3 sources
Federated Averaging with Server Momentum aka FedAvgM, Server Momentum Federated Averaging… A federated optimization algorithm (FedAvgM; Hsu, Qi, and Brown, 2019) that augments Federated Averaging with a Polyak heavy-ball momentum b…	Curated	Algorithms	`AIMech:FedAvgMServerMomentumFederatedAveraging`	4 claims 3 sources
Federated Learning A deep neural network trained across decentralized edge devices or servers holding local data samples without exchanging them.	AIO	Network	`AIO:FederatedLearning`	Imported
Federated LLM aka Federated Large Language Model, decentralized training… A large language model that is trained in a decentralized manner across multiple devices or silos without directly sharing private data enab…	AIO	Model	`AIO:FederatedLLM`	Imported
FedETF (Neural-Collapse-Inspired Federated Learning with Synthetic Fixed Simplex ETF Classifier) aka FedETF, Simplex Equiangular Tight Frame Federated Learning… A neural-collapse-inspired federated learning algorithm (Li et al. 2023, Sections 3.2-4.2, Definition 3.1, Equations 3-11, Algorithms 1-2) t…	Curated	Algorithms	`AIMech:FedEtfNeuralCollapseSimplexEquiangularTightFrameClassifierForFederatedLearning`	4 claims 3 sources
FedEx Weight-Sharing Exponentiated Gradient for Federated Hyperparameter Tuning aka FedEx, FedEx Federated Hyperparameter Tuning… A federated hyperparameter optimization algorithm (Khodak, Tu, Li, Li, Balcan, Smith, & Talwalkar, 2021) that decomposes federated learning…	Curated	Algorithms	`AIMech:FedExWeightSharingExponentiatedGradientForFederatedHyperparameterTuning`	4 claims 3 sources
FedExP (Federated Extrapolation for Speeding Up Federated Averaging) aka FedExP, Federated Extrapolation… A hyperparameter-free adaptive server step-size method for federated optimization (Jhunjhunwala, Wang, & Joshi 2023, Section 3, Equations 4-…	Curated	Algorithms	`AIMech:FedExpExtrapolatedServerAveragingForFederatedLearning`	4 claims 3 sources
FedFA (Federated Feature Augmentation and Momentum-Queued Feature Anchor Loss) aka FedFA, Federated Feature Augmentation… A federated learning algorithm for heterogeneous client distributions (Zhou & Konukoglu 2023, Sections 3.1-3.3, Equations 4-15, Lemma 1, Alg…	Curated	Algorithms	`AIMech:FedFaFederatedFeatureAugmentationAndMomentumQueuedAnchorLoss`	4 claims 3 sources
FedFomo (Personalized Federated Learning with First-Order Model Optimization) aka FedFomo, First-Order Model Optimization for Personalized Federated Learning… A personalized federated learning algorithm (Zhang et al. 2021, Section 3.1 & Appendix A.1, Equations 1-13, Algorithm 1) in which each clien…	Curated	Algorithms	`AIMech:FedFomoFirstOrderModelOptimizationForPersonalizedFederatedLearning`	4 claims 3 sources
FedFTG (Data-Free Global Model Fine-Tuning via Hard Sample Mining Knowledge Distillation) aka FedFTG, Fine-Tuning Global Model via Data-Free Knowledge Distillation… A server-side data-free knowledge distillation algorithm for non-IID federated learning (Zhang, Shen, Ding, Tao, & Duan 2022, Section 4, Equ…	Curated	Algorithms	`AIMech:FedFtgDataFreeGlobalModelFineTuningViaHardSampleMiningKnowledgeDistillation`	4 claims 3 sources
FedFV (Federated Fair Averaging via Loss-Ordered Internal and Historical External Gradient Projection) aka FedFV, Federated Fair Averaging… A fair federated optimization algorithm (Wang, Fan, Qi, Wen, Wang, & Yu 2021, Section 3, Definitions 1-3, Algorithms 1-3, Theorems 1-4) that…	Curated	Algorithms	`AIMech:FedFvFederatedFairAveragingViaLossOrderedAndHistoricalGradientProjection`	4 claims 3 sources
FedGen (Data-Free Knowledge Distillation for Heterogeneous Federated Learning) aka FedGen, Data-Free Knowledge Distillation for Heterogeneous Federated Learning… A data-free knowledge distillation algorithm for heterogeneous federated learning (Zhu, Hong, & Zhou 2021, Section 3, Algorithm 1) in which…	Curated	Algorithms	`AIMech:FedGenDataFreeKnowledgeDistillationForHeterogeneousFederatedLearning`	4 claims 3 sources
FedGKT (Group Knowledge Transfer for Federated Learning of Large CNNs at the Edge) aka FedGKT, Group Knowledge Transfer… An alternating-minimization federated learning and split-knowledge-transfer algorithm (He, Annavaram, & Avestimehr 2020, Section 3, Equation…	Curated	Algorithms	`AIMech:FedGktGroupKnowledgeTransferForEdgeFederatedLearning`	3 claims 3 sources
FedGNN (Federated Graph Neural Network for Privacy-Preserving Recommendation) aka FedGNN, Federated Graph Neural Network for Privacy-Preserving Recommendation FedGNN (Federated Graph Neural Network for Privacy-Preserving Recommendation) is a federated collaborative filtering and graph neural networ…	Curated	Algorithms	`AIMech:FedGnnFederatedGraphNeuralNetworkForPrivacyPreservingRecommendation`	3 claims 3 sources
FedHM: Efficient Federated Learning for Heterogeneous Models via Low-Rank Factorization aka FedHM, Federated Learning for Heterogeneous Models via Low-Rank Factorization… A model-heterogeneous federated learning framework (FedHM; Yao, Pan, O'Neill, Dai, Wan, Jin, and Sun, 2021) that compresses an L-layer globa…	Curated	Algorithms	`AIMech:FedHmHeterogeneousFederatedLearningViaLowRankFactorization`	4 claims 3 sources
FedIIR (Out-of-Distribution Generalization of Federated Learning via Implicit Invariant Relationships) aka FedIIR, Federated Implicit Invariant Relationships… An out-of-distribution (OOD) federated learning algorithm (Guo et al. 2023, Sections 3.1-4.2, Definition 1, Theorems 2-5, Algorithm 1) that…	Curated	Algorithms	`AIMech:FedIirImplicitInvariantRelationshipsForOutOfDistributionFederatedLearning`	4 claims 3 sources
FedKD: Communication-Efficient Federated Learning via Knowledge Distillation aka FedKD, Adaptive Mutual Distillation with Dynamic SVD Gradient Compression Federated Learning… A communication-efficient federated learning algorithm (FedKD; Wu, Wu, Lyu, Huang, and Xie, Nature Communications 2022) in which each client…	Curated	Algorithms	`AIMech:FedKdCommunicationEfficientFederatedLearningViaKnowledgeDistillation`	4 claims 3 sources
FedLC (Federated Learning via Logits Calibration for Label Distribution Skew) aka FedLC, Federated Learning via Logits Calibration… A label-skew-calibrated federated learning algorithm (Zhang et al. 2022, Sections 3-4, Definitions 1-3, Theorems 1-3, Equations 1-8) that mi…	Curated	Algorithms	`AIMech:FedLcLogitsCalibrationForLabelDistributionSkewInFederatedLearning`	4 claims 3 sources
FedLin (Federated Linearized Learning with Client Heterogeneity and Gradient Sparsification) aka FedLin, Federated Linearized Learning… A federated optimization algorithm (Mitra et al. 2021, Section 3, Algorithm 1, Equation 8; Section 4, Algorithms 2-3) that resolves the spee…	Curated	Algorithms	`AIMech:FedLinFederatedLinearizedLearningWithClientHeterogeneityAndGradientSparsification`	4 claims 3 sources
FedMA (Federated Matched Averaging via Layer-Wise Bayesian Nonparametric Matching) aka FedMA, Federated Matched Averaging… A layer-wise permutation-aware federated learning algorithm (FedMA, Algorithm 1) for modern neural networks (FC layers, CNN channels, and RN…	Curated	Algorithms	`AIMech:FedMaFederatedMatchedAveragingViaLayerWiseBayesianNonparametricMatching`	4 claims 3 sources
FedMAX (Maximum-Entropy Activation Divergence Mitigation in Federated Learning) aka FedMAX, Maximum Entropy Activation Regularized Federated Learning… A non-IID federated learning regularization algorithm (Chen, Bhardwaj, & Marculescu 2020, Section 3, Equations 1-4) that mitigates cross-cli…	Curated	Algorithms	`AIMech:FedMaxMaximumEntropyActivationDivergenceMitigationInFederatedLearning`	4 claims 3 sources
FedMD (Heterogeneous Federated Learning via Public-Dataset Model Distillation) aka FedMD, Heterogeneous Federated Learning via Model Distillation… A model-heterogeneous federated learning framework (Li & Wang 2019, Section 3, Algorithm 1, Figure 2) in which each client k in {1, ..., m}…	Curated	Algorithms	`AIMech:FedMdHeterogeneousFederatedLearningViaPublicDatasetModelDistillation`	4 claims 3 sources
FedMGDA+ (Multi-Objective Pareto-Stationary Federated Learning with Normalized Multiple Gradient Descent) aka FedMGDA+, FedMGDA and MGDA-Prox… A multi-objective federated optimization algorithm (Hu, Shaloudegi, Zhang, & Yu 2022, Sections 3-5, Definition 1, Lemma 1, Equations 4-9 & 1…	Curated	Algorithms	`AIMech:FedMgdaPlusMultiObjectiveParetoStationaryFederatedOptimization`	4 claims 3 sources
FedMix (Approximation of Mixup under Mean Augmented Federated Learning) aka FedMix, Federated Mixup under Mean Augmented Federated Learning… A privacy-preserving federated data augmentation and optimization algorithm (Yoon, Shin, Hwang, & Yang 2021, Section 3, Proposition 1, Equat…	Curated	Algorithms	`AIMech:FedMixApproximationOfMixupUnderMeanAugmentedFederatedLearning`	4 claims 3 sources
FedNL (Federated Newton Learn) aka FedNL, Federated Newton Learn… FedNL (Federated Newton Learn) is a family of communication-efficient second-order federated optimization algorithms for solving general fin…	Curated	Algorithms	`AIMech:FedNlFederatedNewtonLearnWithCompressedHessianLearning`	4 claims 3 sources
FedNova Normalized Averaging for Heterogeneous Federated Optimization aka FedNova, Federated Normalized Averaging… A heterogeneous federated optimization framework and normalized averaging algorithm (FedNova) that models client i's cumulative local model…	Curated	Algorithms	`AIMech:FedNovaNormalizedAveragingForHeterogeneousFederatedOptimization`	4 claims 3 sources
FedNTD (Federated Not-True Distillation for Global Knowledge Preservation) aka FedNTD, Federated Not-True Distillation… A heterogeneous federated learning algorithm (Lee et al. 2022, Section 3, Equations 10-14, Algorithm 1) that mitigates catastrophic forgetti…	Curated	Algorithms	`AIMech:FedNtdNotTrueDistillationForFederatedLearning`	4 claims 3 sources
FedOpt Adaptive Server Optimization (FedAdagrad, FedYogi, and FedAdam) aka FedOpt, FedAdagrad… A general client-server federated optimization framework (FedOpt) and its adaptive server-side instantiations (FedAdagrad, FedYogi, and FedA…	Curated	Algorithms	`AIMech:FedOptAdaptiveServerOptimizationFedAdagradFedYogiFedAdam`	4 claims 3 sources
FedPA (Federated Posterior Averaging via Local MCMC and Shrinkage Covariance) aka FedPA, Federated Posterior Averaging… A Bayesian posterior-inference federated learning algorithm (Al-Shedivat et al. 2021, Algorithms 1-2) that decomposes the global posterior u…	Curated	Algorithms	`AIMech:FedPaFederatedPosteriorAveragingViaLocalMcmcAndShrinkageCovariance`	4 claims 3 sources
FedPAC (Personalized Federated Learning with Feature Alignment and Classifier Collaboration) aka FedPAC, Feature Alignment and Classifier Collaboration in Personalized Federated Learning… A personalized federated learning algorithm (Xu, Tong, & Huang 2023, Sections 3-4, Theorem 1, Equations 3-4, 10-19, 43-46) that jointly (1)…	Curated	Algorithms	`AIMech:FedPacFeatureAlignmentAndClassifierCollaborationForPersonalizedFederatedLearning`	4 claims 3 sources
FedPAGE Probabilistic Local Stochastic Gradient Method for Federated Learning aka FedPAGE, Federated Probabilistic Gradient Estimator… A communication-efficient local stochastic gradient method for federated convex and nonconvex optimization (Algorithm 1) that generalizes th…	Curated	Algorithms	`AIMech:FedPageProbabilisticLocalGradientMethodForFederatedLearning`	4 claims 3 sources
FedPara and pFedPara (Low-Rank Hadamard Product Parameterization for Federated Learning) aka FedPara and pFedPara, FedPara… A communication-efficient layer parameterization for federated learning and its personalized variant (Hyeon-Woo, Ye-Bin, & Oh 2022, Section…	Curated	Algorithms	`AIMech:FedParaAndPFedParaLowRankHadamardProductParameterization`	4 claims 3 sources
FedPD (Federated Primal-Dual Optimization with Adaptivity to Non-IID Data) aka FedPD, Federated Primal-Dual Optimization… A primal-dual federated optimization framework (Zhang et al. 2021, Algorithm 1) for smooth possibly non-convex consensus problems min_{x_0,…	Curated	Algorithms	`AIMech:FedPdFederatedPrimalDualOptimizationWithAdaptivityToNonIidData`	4 claims 3 sources
FedPer (Federated Learning with Personalization Layers) aka FedPer, Federated Learning with Personalization Layers… A personalized federated deep learning algorithm (Arivazhagan, Aggarwal, Singh, & Choudhary 2019, Section 3, Equations 1-3, Algorithms 1-2)…	Curated	Algorithms	`AIMech:FedPerFederatedLearningWithPersonalizationLayers`	4 claims 3 sources
FedPop and FedSOUK (Bayesian Mixed-Effects Population Personalized Federated Learning) aka FedPop, FedSOUK… A Bayesian mixed-effects population modeling framework and stochastic optimization / compressed Langevin Markov chain Monte Carlo algorithm…	Curated	Algorithms	`AIMech:FedPopAndFedSoukBayesianHierarchicalPopulationPersonalizedFederatedLearning`	4 claims 3 sources
FedProto (Federated Prototype Learning across Heterogeneous Clients) aka FedProto, Federated Prototype Learning… A gradient-free and parameter-free heterogeneous federated learning framework (Tan, Long, Liu, Zhou, Lu, Jiang, & Zhang 2022, Sections Probl…	Curated	Algorithms	`AIMech:FedProtoFederatedPrototypeLearningAcrossHeterogeneousClients`	4 claims 3 sources
FedProx Proximal Heterogeneous Federated Optimization with Variable Inexact Local Work aka FedProx, Federated Proximal Optimization… A federated optimization framework (FedProx) for statistically and systemically heterogeneous networks in which each round t samples K devic…	Curated	Algorithms	`AIMech:FedProxProximalHeterogeneousFederatedOptimization`	4 claims 3 sources
FedRecon (Federated Reconstruction for Partially Local Federated Learning) aka FedRecon, Federated Reconstruction… A stateless partially local federated learning framework (Singhal, Sidahmed, Garrett, Wu, Rush, & Prakash 2021, Sections 3-4, Equations 1-2,…	Curated	Algorithms	`AIMech:FedReconFederatedReconstructionForPartiallyLocalFederatedLearning`	4 claims 3 sources
FedRep (Exploiting Shared Representations for Personalized Federated Learning) aka FedRep, Federated Representation Learning via Alternating Minimization-Descent… A personalized federated learning algorithm (FedRep, Algorithm 1 and Algorithm 2) that decomposes each client i's model into a shared global…	Curated	Algorithms	`AIMech:FedRepExploitingSharedRepresentationsForPersonalizedFederatedLearning`	4 claims 3 sources
FedRolex (Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction) aka FedRolex, Rolling Sub-Model Extraction Federated Learning… A partial-training (PT) model-heterogeneous federated learning algorithm (Alam, Liu, Yan, & Zhang 2022, Section 3, Equations 3-6, Algorithm…	Curated	Algorithms	`AIMech:FedRolexModelHeterogeneousFederatedLearningWithRollingSubModelExtraction`	4 claims 3 sources
FedSage+ (Subgraph Federated Learning with Missing Neighbor Generation) aka FedSage+, FedSage Plus… FedSage+ is a subgraph federated learning algorithm for collaborative node classification across M data owners holding disjoint local subgra…	Curated	Algorithms	`AIMech:FedSagePlusSubgraphFederatedLearningWithMissingNeighborGeneration`	4 claims 3 sources
FedSAM and FedASAM (Sharpness-Aware Minimization and Server Stochastic Weight Averaging for Federated Learning) aka FedSAM, FedASAM… A sharpness-aware federated optimization framework (Caldarola, Caputo, & Ciccone 2022, Sections 3-4, Equations 1-5, Algorithm 1) that mitiga…	Curated	Algorithms	`AIMech:FedSamAndFedAsamSharpnessAwareMinimizationAndStochasticWeightAveragingForFederatedLearning`	4 claims 3 sources
FedShuffle and FedShuffleMVR Objective-Consistent Local Random Reshuffling for Federated Learning aka FedShuffle, FedShuffleMVR… A family of federated local-epoch optimization algorithms with without-replacement Random Reshuffling (FedShuffle in Algorithm 1/3, its Mome…	Curated	Algorithms	`AIMech:FedShuffleAndFedShuffleMvrObjectiveConsistentLocalRandomReshufflingForFederatedLearning`	4 claims 3 sources
FedSpeed (Prox-Correction and Extra-Gradient Perturbation for Federated Learning) aka FedSpeed, FedSpeed Prox-Correction and Gradient Perturbation… A non-convex federated optimization algorithm (Sun et al. 2023, Sections 3-4, Equations 2-5, Algorithm 1, Theorem 4.4, Corollary 4.5) that e…	Curated	Algorithms	`AIMech:FedSpeedProxCorrectionAndGradientPerturbationForFederatedLearning`	4 claims 3 sources
FedSplit (Operator Splitting for Fast Federated Optimization) aka FedSplit, Peaceman-Rachford Federated Operator Splitting… An operator-splitting federated optimization algorithm (Pathak & Wainwright 2020, Algorithm 1) that reformulates finite-sum federated minimi…	Curated	Algorithms	`AIMech:FedSplitOperatorSplittingForFastFederatedOptimization`	4 claims 3 sources
FedSR Simple Representation Regularization for Federated Domain Generalization aka FedSR, FedL2R and FedCMI… A decentralized federated domain generalization method (Nguyen, Torr, & Lim, 2022) that trains a probabilistic representation encoder p(z\|x)…	Curated	Algorithms	`AIMech:FedSrSimpleAndEffectiveDomainGeneralizationForFederatedLearning`	4 claims 3 sources
FedTHE (Test-Time Robust Personalized Federated Learning with Two-Head Ensemble) aka FedTHE, FedTHE+… A test-time adaptive personalized federated learning framework (Jiang & Lin 2023, Sections 4.1-4.2, Algorithm 1) that equips a shared featur…	Curated	Algorithms	`AIMech:FedTheTestTimeHeadEnsembleForPersonalizedFederatedLearning`	4 claims 3 sources
FedU and dFedU (Laplacian-Regularized Federated Multi-Task Learning) aka FedU, dFedU… A communication-centralized (FedU, Algorithm 1) and decentralized (dFedU, Algorithm 2) federated multi-task learning framework (Dinh, Vu, Tr…	Curated	Algorithms	`AIMech:FedUAndDFedULaplacianRegularizedFederatedMultiTaskLearning`	4 claims 3 sources
FedWeIT (Federated Weighted Inter-Client Transfer) aka FedWeIT, Federated Weighted Inter-Client Transfer… FedWeIT (Federated Weighted Inter-Client Transfer) is a parameter-decomposed federated continual learning algorithm that enables distributed…	Curated	Algorithms	`AIMech:FedWeitFederatedContinualLearningWithWeightedInterClientTransfer`	4 claims 3 sources
Feedback Loop Bias A use and interpretation bias occurring when an algorithm learns from user behavior and feeds that behavior back into the model.	AIO	Bias	`AIO:FeedbackLoopBias`	Imported
Feedback Network aka FBN An artificial neural network that refines its representations iteratively based on feedback from previous outputs.	AIO	Network	`AIO:FeedbackNetwork`	Imported
FetchSGD (Count-Sketch Gradient Compression with Server Momentum and Error Accumulation) aka FetchSGD, FedSketchedSGD… A stateless communication-efficient federated optimization algorithm (FetchSGD, Algorithm 1) in which each participating client i in [W] com…	Curated	Algorithms	`AIMech:FetchSgdCountSketchGradientCompressionWithServerMomentumAndErrorAccumulation`	4 claims 3 sources
FFA-LoRA: Federated Freeze-A Low-Rank Adaptation aka FFA-LoRA, Federated Freeze A LoRA… A parameter-efficient and differentially private federated fine-tuning algorithm (Federated Freeze A LoRA / FFA-LoRA; Sun, Li, Li, and Ding,…	Curated	Algorithms	`AIMech:FfaLoraFederatedFreezeALowRankAdaptation`	4 claims 3 sources
Fill algorithm An idealized finite constraint-satisfaction search algorithm that takes any strictly cost-reducing single-variable change when available and…	Curated	Algorithms	`AIMech:FillAlgorithm`	1 claim 1 source
FiLM Parameter-Arithmetic Inference A post-training visual-question-answering procedure that uses a parser to construct related questions and combines their generated FiLM scal…	Curated	Algorithms	`AIMech:FiLMParameterArithmeticInference`	5 claims 1 source
Finite-Time Extremal Index, Cluster Size, and Sojourn Time in Non-Markovian Regenerative Processes aka Finite-Time Extremal Index Reciprocity and Sojourn Identity in Regenerative Models, Abadi-Freitas Non-Markovian Regenerative Extremal Clustering Formulation A probabilistic extreme-value and quantitative-recurrence formulation for stationary discrete-time non-Markovian regenerative processes (X_n…	Curated	Mathematical Methods	`AIMech:FiniteTimeExtremalIndexClusterSizeAndSojournTimeInRegenerativeProcesses`	4 claims 3 sources
Fira (Full-Rank Training under Low-Rank Optimizer Constraint) aka Fira, Fira Optimizer Framework… A memory-efficient full-rank neural network optimization framework that maintains adaptive optimizer states strictly within a low-rank gradi…	Curated	Algorithms	`AIMech:FiraFullRankTrainingUnderLowRankOptimizerConstraint`	5 claims 3 sources
First-come, first-served beam decoding aka FCFS beam decoding The sequence beam-decoding procedure described by Kasai and colleagues that stores completed hypotheses separately from the continuing beam…	Curated	Algorithms	`AIMech:FCFSBeamDecoding`	2 claims 2 sources
FISH Mask aka Fisher-Induced Sparse uncHanging Mask, FISH Mask Training… A sparse gradient-based neural network training and parameter-efficient transfer learning algorithm (Fisher-Induced Sparse uncHanging Mask)…	Curated	Algorithms	`AIMech:FISHMask`	3 claims 3 sources
Fixed Effects Model aka FEM A regression analysis in which the model parameters are fixed or non-random quantities.	AIO	MachineLearningTask	`AIO:FixedEffectsModel`	Imported
Fixed-Component Mixture-Weight EM aka Mixture-Weight Expectation Maximization An expectation-maximization specialization that keeps every component distribution fixed and updates only their simplex mixing weights by av…	Curated	Algorithms	`AIMech:FixedComponentMixtureWeightEM`	3 claims 1 source
Fixed-length Poisson Markov random field aka LPMRF, Fixed-length Poisson MRF A finite-total count distribution whose probability on nonnegative integer vectors summing to a specified total is proportional to a Poisson…	Curated	Model Families	`AIMech:FixedLengthPoissonMarkovRandomField`	1 claim 2 sources
Fixed-length Poisson MRF topic model aka LPMRF topic model A probabilistic topic model that allocates a document total among topics, draws an independent fixed-length Poisson-MRF count vector for eac…	Curated	Model Families	`AIMech:FixedLengthPoissonMRFTopicModel`	1 claim 2 sources
FixMatch A semi-supervised classifier-training procedure that fits labeled examples and trains on strongly augmented unlabeled inputs using hard pseu…	Curated	Algorithms	`AIMech:FixMatch`	2 claims 3 sources
FjORD (Fair and Accurate Federated Learning under Heterogeneous Targets with Ordered Dropout) aka FjORD, Federated Learning with Ordered Dropout… A system-heterogeneous federated learning method (Horvath, Laskaridis, Almeida, Leontiadis, Venieris, & Lane 2021, Sections 3-4, Equation 1,…	Curated	Algorithms	`AIMech:FjordOrderedDropoutAndSelfDistillationForHeterogeneousFederatedLearning`	4 claims 3 sources
Flake exact-flow community identification aka EXACT-FLOW-COMMUNITY, Flake exact-flow community algorithm A seeded web-graph grouping procedure that adds infinite-capacity source arcs to seed vertices, makes original hyperlink connections bidirec…	Curated	Algorithms	`AIMech:FlakeExactFlowCommunity`	6 claims 2 sources
Flake focused community crawling aka APPROXIMATE-FLOW-COMMUNITY, Flake focused-crawl algorithm A flow-based focused-crawling family that alternates gathering a local web graph around positive seed pages, extracting a group through seed…	Curated	Algorithms	`AIMech:FlakeFocusedCrawl`	7 claims 2 sources
FLAME Dynamic Clustering and Adaptive Clipping-Noising Backdoor Defense aka FLAME Taming Backdoors in Federated Learning, FLAME Federated Backdoor Defense Framework… A three-stage federated learning backdoor defense framework that (1) computes pairwise cosine distances c_ij = 1 - (W_i . W_j)/(\|\|W_i\|\|_2 \|\|…	Curated	Algorithms	`AIMech:FlameDynamicClusteringAndAdaptiveClippingNoisingBackdoorDefense`	4 claims 3 sources
FlashAttention An exact attention computation algorithm using tiling and recomputation to reduce transfers between GPU memory levels.	Curated	Algorithms	`AIMech:FlashAttention`	1 claim 1 source
FlashConv An execution algorithm for state-space sequence convolutions that fuses FFT-based convolution in GPU on-chip memory, uses block FFT matrix m…	Curated	Algorithms	`AIMech:FlashConv`	1 claim 1 source
Flatten Layer A reshaping layer that flattens the input	AIO	Layer	`AIO:FlattenLayer`	Imported
Flattened slice sampling A finite categorical conditional-update algorithm that splits excess probability from a maximum-probability state into additional bars and s…	Curated	Algorithms	`AIMech:FlattenedSliceSampling`	6 claims 1 source
FLDetector Cauchy Mean Value and L-BFGS Model-Update Consistency Detection aka FLDetector, FLDetector Malicious Client Detection via Model-Updates Consistency… An unsupervised server-side malicious-client detection method for federated learning that predicts each client's current gradient update via…	Curated	Algorithms	`AIMech:FlDetectorCauchyMeanValueLbfgsModelUpdateConsistencyDetection`	4 claims 3 sources
Flora Gradient Compression aka FLORA (From LoRA to High-Rank Updates), Flora Resampled Random-Projection Gradient Compression… A memory-efficient neural network optimization algorithm that compresses gradient accumulation and momentum states into an O(n r) sublinear…	Curated	Algorithms	`AIMech:FloraGradientCompression`	4 claims 3 sources
FLoRA: Stacking-Based Federated Fine-Tuning with Heterogeneous Low-Rank Adaptations aka FLoRA, Stacking-Based Federated Heterogeneous LoRA… A noise-free, rank-heterogeneous federated parameter-efficient fine-tuning algorithm (FLoRA; Wang, Shen, He, Sun, Wang, Lyu, and Li, NeurIPS…	Curated	Algorithms	`AIMech:FloraStackingBasedFederatedHeterogeneousLowRankAdaptation`	4 claims 3 sources
Flow matching aka FM (flow matching) A generative-model training method that fits a time-dependent vector field by regression to velocities associated with a chosen probability…	Curated	Algorithms	`AIMech:FlowMatching`	1 claim 1 source
FLTrust (Byzantine-Robust Federated Learning via Trust Bootstrapping) aka FLTrust, Federated Learning via Trust Bootstrapping… FLTrust (Byzantine-Robust Federated Learning via Trust Bootstrapping) is a server-bootstrapped Byzantine-robust federated learning algorithm…	Curated	Algorithms	`AIMech:FlTrustByzantineRobustFederatedLearningViaTrustBootstrapping`	3 claims 3 sources
FocusedILS A ParamILS algorithm-configuration method that adaptively extends paired evaluation prefixes until one configuration dominates the other, an…	Curated	Algorithms	`AIMech:FocusedILS`	1 claim 1 source
FOOF (Fast First-Order Optimizer / First-Order Gradient Descent on Neurons) aka FOOF, Fast First-Order Optimizer… A layer-wise neural network optimization algorithm that performs gradient descent in neuron activation space rather than weight space by sol…	Curated	Algorithms	`AIMech:FoofFirstOrderOnFeaturesNeuronGradientDescentOptimization`	5 claims 3 sources
FoolsGold Cosine-Similarity Sybil Defense for Federated Learning aka FoolsGold, FoolsGold Sybil-Resilient Federated Aggregation… A sybil-resilient federated learning aggregation algorithm that tracks each client's cumulative historical gradient vector H_i = sum_{t=1}^T…	Curated	Algorithms	`AIMech:FoolsGoldCosineSimilaritySybilDefenseForFederatedLearning`	3 claims 3 sources
Forest-structured Dvoretzky-Kiefer-Wolfowitz post hoc confidence bounds aka Forest-structured reference family post hoc false positive bounds, Bilinear bottom-up tree interpolation for post hoc false discovery bounds… A multiple-testing post hoc inference methodology that constructs simultaneous (1 - alpha)-confidence upper bounds V(S) on the number of fal…	Curated	Mathematical Methods	`AIMech:ForestStructuredDKWPostHocConfidenceBounds`	4 claims 3 sources
Fork-convex exchangeability testing via universal safe e-processes aka Fork-Convex Hull Characterization of Composite Test Supermartingales, Jeffreys'-Mixture Universal-Inference Safe E-Process for Exchangeability… A sequential hypothesis testing and game-theoretic probability framework (Ramdas, Ruf, Larsson, & Koolen 2022, International Journal of Appr…	Curated	Mathematical Methods	`AIMech:ForkConvexExchangeabilityTestingBySafeEProcesses`	4 claims 3 sources
FourierFT aka Discrete Fourier Transform Fine-Tuning, Fourier Fine-Tuning… A spectral parameter-efficient fine-tuning algorithm that parameterizes the spatial weight update matrix of a frozen pretrained layer as the…	Curated	Algorithms	`AIMech:FourierFT`	4 claims 3 sources
FractalNet DropPath A structured regularization procedure for fractal networks that trains shared parameters using locally selected nonempty subsets of join inp…	Curated	Algorithms	`AIMech:FractalNetDropPath`	6 claims 1 source
FractionalMaxPool2D Layer aka FractionalMaxPool2D A pooling layer that applies a 2D fractional max pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:FractionalMaxPool2DLayer`	Imported
FractionalMaxPool3D Layer aka FractionalMaxPool3D A pooling layer that applies a 3D fractional max pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:FractionalMaxPool3DLayer`	Imported
Frequent Directions Deterministic Row-Update Matrix Sketching via Singular-Value Shrinkage aka Tail-Residual Frequent Directions Sketching, Fast-FrequentDirections… Frequent Directions (FrequentDirections and Fast-FrequentDirections) is a deterministic row-update streaming matrix sketching algorithm intr…	Curated	Algorithms	`AIMech:FrequentDirectionsDeterministicMatrixSketching`	3 claims 3 sources
Frequent-Directions Deterministic Streaming Matrix Sketching aka Frequent-Directions Matrix Sketching, Liberty Deterministic Covariance Matrix Sketching… Frequent-Directions Deterministic Streaming Matrix Sketching is a deterministic one-pass row-streaming matrix sketching algorithm introduced…	Curated	Algorithms	`AIMech:FrequentDirectionsDeterministicStreamingMatrixSketching`	3 claims 3 sources
Fromage (Frobenius Matched Gradient Descent) aka Fromage Optimizer, Frobenius Matched Gradient Descent… A layerwise relative-trust optimization algorithm for deep neural networks (Algorithm 1) derived from the deep relative trust gradient break…	Curated	Algorithms	`AIMech:FromageFrobeniusMatchedGradientDescentOptimization`	4 claims 3 sources
Full-echo Q-routing An information-exploration modification of tabular Q-routing that queries immediate neighbors whenever a node needs a routing decision and u…	Curated	Algorithms	`AIMech:FullEchoQRouting`	4 claims 1 source
Fully adaptive cross-entropy optimization A named cross-entropy optimization variant, called FACE in the source, that fixes an elite sample count and adapts the number of sampled can…	Curated	Algorithms	`AIMech:FullyAdaptiveCrossEntropyOptimization`	6 claims 1 source
Fully factorized mean-field inference aka Naive mean-field inference, Fully factorized variational inference A variational inference method that restricts its approximating distribution to a product of single-variable factors and adjusts those facto…	Curated	Mathematical Methods	`AIMech:FullyFactorizedMeanFieldInference`	1 claim 1 source
Fully visible sigmoid belief network aka FVSBN, Logistic autoregressive Bayesian network A fully observed binary autoregressive probabilistic model whose conditional probability at each position is a logistic function of a bias a…	Curated	Architectures	`AIMech:FullyVisibleSigmoidBeliefNetwork`	1 claim 3 sources
Funding Bias A group bias arising when biased results are reported to support or satisfy the funding agency or financial supporter of a research study.	AIO	Bias	`AIO:FundingBias`	Imported
GaLore (Gradient Low-Rank Projection) aka GaLore, Gradient Low-Rank Projection… A memory-efficient full-parameter training strategy (Definitions 3.6 and Algorithm 2) for large language models and deep neural networks tha…	Curated	Algorithms	`AIMech:GaLoreGradientLowRankProjectionForMemoryEfficientLlmTraining`	4 claims 3 sources
Gamma filter aka Adaptive gamma filter, ADALINE(μ) A linear adaptive filter family that combines a direct input tap with weighted cascaded first-order gamma-memory traces, using one shared me…	Curated	Model Families	`AIMech:GammaFilter`	6 claims 1 source
Gamma neural model aka Gamma neural network, Gamma net… A neural architecture family that represents delayed inputs or neural outputs by weighted gamma-kernel memory traces, realized through casca…	Curated	Architectures	`AIMech:GammaNeuralModel`	6 claims 2 sources
GAR Generation-Augmented Retrieval for Open-Domain Question Answering aka GAR, Generation-Augmented Retrieval… A query-expansion and retrieval algorithm for open-domain question answering that trains sequence-to-sequence pre-trained language models (s…	Curated	Algorithms	`AIMech:GARGenerationAugmentedRetrievalForOpenDomainQA`	4 claims 3 sources
Gated Graph Neural Network aka GG-NN, Gated Graph Neural Networks A graph neural architecture that initializes node states from annotations, repeatedly combines edge-type- and direction-specific neighbor me…	Curated	Architectures	`AIMech:GatedGraphNeuralNetwork`	6 claims 1 source
Gated Graph Sequence Neural Network aka GGS-NN, Gated Graph Sequence Neural Networks A graph-to-sequence neural architecture that repeatedly runs gated graph propagation to predict an output and update node annotations, using…	Curated	Architectures	`AIMech:GatedGraphSequenceNeuralNetwork`	6 claims 1 source
Gated Recurrent Unit aka GRU A long short-term memory network that is a gating mechanism in recurrent neural networks similar to LSTMs but with fewer parameters and no o…	AIO	Network	`AIO:GatedRecurrentUnit`	Imported
Gated-feedback recurrent neural network aka GF-RNN A layered recurrent architecture in which learned input-dependent scalar gates modulate recurrent projections from every previous layer stat…	Curated	Architectures	`AIMech:GatedFeedbackRecurrentNeuralNetwork`	6 claims 1 source
Gaussian Differentiable Pooling A spatial pooling and unpooling component whose nonnegative, unit-L2 weights are square-root normalized axis-aligned Gaussian samples, with…	Curated	Layers & Modules	`AIMech:GaussianDifferentiablePooling`	5 claims 1 source
Gaussian Factor Analysis aka Linear Gaussian Factor Analysis A linear Gaussian latent-variable model in which observed variables share a lower-dimensional Gaussian factor and have conditionally indepen…	Curated	Model Families	`AIMech:GaussianFactorAnalysis`	4 claims 1 source
Gaussian loss-smoothed mixed-model variational inference aka NCVB-UF A nonconjugate variational inference procedure for a loss-defined mixed-effects generalized posterior that retains a joint Gaussian over fix…	Curated	Algorithms	`AIMech:GaussianLossSmoothedMixedModelVariationalInference`	7 claims 2 sources
Gaussian message conflict diagnostic A Bayesian GLMM screening procedure that separates Gaussian prior and likelihood natural-parameter messages at local variational fixed point…	Curated	Algorithms	`AIMech:GaussianMessageConflictDiagnostic`	7 claims 3 sources
Gaussian process regression aka GPR Probabilistic regression conditioning a Gaussian-process prior on observed training data.	Curated	Model Families	`AIMech:GaussianProcessRegression`	1 claim 1 source
Gaussian-process moment matching for Gaussian inputs aka Gaussian input Gaussian process moment matching A Gaussian-process prediction procedure that analytically integrates a fixed squared-exponential posterior over an independently prescribed…	Curated	Algorithms	`AIMech:GaussianProcessGaussianInputMomentMatching`	5 claims 3 sources
GaussianDropout Layer A regularization layer that applies multiplicative 1-centered Gaussian noise.	AIO	Layer	`AIO:GaussianDropoutLayer`	Imported
GaussianNoise Layer A regularization layer that applies additive zero-centered Gaussian noise.	AIO	Layer	`AIO:GaussianNoiseLayer`	Imported
GCFL+ (Gradient Sequence Dynamic Time Warping Clustered Federated Graph Classification) aka GCFL+, GCFL Plus… GCFL+ is a dynamic clustered federated graph classification algorithm for clients holding structure- and feature-heterogeneous (non-IID) gra…	Curated	Algorithms	`AIMech:GcflPlusGradientSequenceDynamicTimeWarpingClusteredFederatedGraphClassification`	4 claims 3 sources
GELU Function aka GELU, Gaussian Error Linear Unit A mathematical function that computes x * P(X <= x) where P(X) ~ N(0 1) weighting inputs by their value rather than gating inputs by their s…	AIO	MathematicalFunction	`AIO:GELUFunction`	Imported
Generalized advantage estimation aka GAE An advantage-function estimator for policy-gradient learning formed from an exponentially weighted sum of temporal-difference residuals.	Curated	Mathematical Methods	`AIMech:GeneralizedAdvantageEstimation`	1 claim 1 source
Generalized Alternating Minimization aka GAM (generalized alternating minimization) An information-geometric fitting framework that updates a generating distribution constrained by the observations and model parameters to de…	Curated	Algorithms	`AIMech:GeneralizedAlternatingMinimization`	4 claims 1 source
Generalized Autoregressive Conditional Heteroskedasticity aka GARCH A model that incorporates lagged conditional variances, allowing for more flexibility in modeling time-varying volatility.	AIO	Model	`AIO:GeneralizedAutoregressiveConditionalHeteroskedasticity`	Imported
Generalized Bernstein-Orlicz sub-Weibull concentration and high-dimensional misspecified Lasso aka Generalized Bernstein-Orlicz (GBO) Norm and Sub-Weibull Concentration, Sub-Weibull GBO Norm and High-Dimensional Covariance and Lasso Framework… Generalized Bernstein-Orlicz sub-Weibull concentration and high-dimensional misspecified Lasso is a non-asymptotic heavy-tailed probability…	Curated	Mathematical Methods	`AIMech:GeneralizedBernsteinOrliczSubWeibullConcentrationAndHighDimensionalLasso`	4 claims 3 sources
Generalized component analysis aka GCA An undirected latent-component model family coupling categorical text and heterogeneous document attributes to positive lognormal hidden var…	Curated	Model Families	`AIMech:GeneralizedComponentAnalysis`	3 claims 1 source
Generalized core vector machine aka Generalized CVM, Generalized core vector machines A kernel optimization algorithm that converts a quadratic program with a positive-semidefinite Gram matrix and simplex constraints into a ce…	Curated	Algorithms	`AIMech:GeneralizedCoreVectorMachine`	5 claims 2 sources
Generalized Expectation Maximization aka Generalized EM, GEM (generalized expectation maximization) A latent-variable likelihood-fitting framework that computes the expected complete-data log likelihood under the current exact posterior and…	Curated	Algorithms	`AIMech:GeneralizedExpectationMaximization`	3 claims 2 sources
Generalized Few-shot Learning aka GFSL A deep neural network that learns novel classes from few samples per class, preventing catastrophic forgetting of base classes and ensuring…	AIO	Network	`AIO:GeneralizedFewshotLearning`	Imported
Generalized Linear Model aka GLM A regression analysis that relates the linear model to the response variable via a link function and allowing the variance of each measureme…	AIO	MachineLearningTask	`AIO:GeneralizedLinearModel`	Imported
Generalized LoRA aka GLoRA, One-for-All Generalized Low-Rank Adaptation… A unified parameter-efficient fine-tuning framework that adapts each pretrained linear layer f(x) = W_0 x + b_0 using five configurable supp…	Curated	Algorithms	`AIMech:GLoRA`	4 claims 3 sources
Generalized mean p-value merging aka Power Mean P-Value Combination, Kolmogorov Generalized Mean P-Merging Function… A statistical p-value combination framework (Vovk & Wang 2020) that aggregates K arbitrarily dependent hypothesis test p-values p_1, ..., p_…	Curated	Mathematical Methods	`AIMech:GeneralizedMeanPValueMerging`	4 claims 3 sources
Generalized root model aka Generalized root graphical model A family of finite undirected probability models that retains univariate exponential-family base measures and couples coordinatewise roots o…	Curated	Model Families	`AIMech:GeneralizedRootModel`	1 claim 1 source
Generative Adversarial Network aka GAN An unsupervised pretrained network framework where two neural networks contest in a game to generate new data with the same statistics as th…	AIO	Network	`AIO:GenerativeAdversarialNetwork`	Imported
Generative Adversarial Network-Augmented LLM aka GAN-Large Language Model, Generative Adversarial Network-Augmented Large Language Model… A large language model which incorporates a generative adversarial network (GAN) into its training process, using a discriminator network to…	AIO	Model	`AIO:GenerativeAdversarialNetworkAugmentedLLM`	Imported
Generative Commonsense LLM aka Generative Commonsense Large Language Model, World Model… A large language model that is trained to understand and model basic physics causality and common sense about how the real world works.	AIO	Model	`AIO:GenerativeCommonsenseLLM`	Imported
Generative Language Interface aka Interactive generation A language model that enables users to engage in an interactive dialogue with an LLM providing feedback to guide and refine the generated ou…	AIO	Model	`AIO:GenerativeLanguageInterface`	Imported
Generative Topographic Mapping aka GTM A nonlinear latent-variable density model with a uniform discrete prior on fixed latent grid nodes, mapped through a shared smooth function…	Curated	Model Families	`AIMech:GenerativeTopographicMapping`	4 claims 1 source
Generic lazy-neighbor agglomerative clustering aka Generic linkage algorithm (Müllner), GENERIC_LINKAGE An agglomerative clustering algorithm that caches candidate nearest neighbors and lower bounds on row-minimum dissimilarities in a priority…	Curated	Algorithms	`AIMech:GenericLazyNeighborAgglomerativeClustering`	6 claims 3 sources
Generic tree sampling aka Chen generic sampling, Generic importance-weighted tree sampling An importance-sampling generalization of Chen heuristic tree sampling that merges representatives of ordered tree strata using specified pos…	Curated	Algorithms	`AIMech:GenericTreeSampling`	5 claims 1 source
GENET A connectionist architecture for finite constraint satisfaction that represents variable assignments by active label nodes and alternates in…	Curated	Architectures	`AIMech:GENET`	1 claim 1 source
Genetic algorithm aka GA Evolutionary optimization using fitness-based selection and genetic variation of candidate solutions.	Curated	Algorithms	`AIMech:GeneticAlgorithm`	1 claim 1 source
Genie clustering aka Genie linkage, Genie hierarchical clustering An agglomerative clustering algorithm that normally selects a nearest pair by single-link distance and, when cluster-size inequality exceeds…	Curated	Algorithms	`AIMech:GenieClustering`	6 claims 4 sources
Gibbs sampling aka Gibbs sampler A Markov chain Monte Carlo algorithm that repeatedly draws a coordinate or block from its full conditional distribution given the current va…	Curated	Algorithms	`AIMech:GibbsSampling`	2 claims 2 sources
Girvan–Newman community detection aka Girvan–Newman algorithm, edge-betweenness community detection A divisive community-detection algorithm that repeatedly removes an edge with maximal current shortest-path betweenness and recalculates aff…	Curated	Algorithms	`AIMech:GirvanNewmanCommunityDetection`	6 claims 1 source
GLFC (Global-Local Forgetting Compensation) aka GLFC, Global-Local Forgetting Compensation… GLFC (Global-Local Forgetting Compensation) is a federated class-incremental learning (FCIL) algorithm that mitigates both local catastrophi…	Curated	Algorithms	`AIMech:GlfcGlobalLocalForgettingCompensationForFederatedClassIncrementalLearning`	4 claims 3 sources
Global Convergence and Stationary-Point Characterization of EM for Two-Component Gaussian Mixtures aka Global Convergence of EM for Two-Gaussian Mixtures, Xu-Hsu-Maleki Global EM Trajectory and Saddle-Hyperplane Analysis… A global dynamical and statistical consistency analysis (introduced by Ji Xu, Daniel J. Hsu, and Arian Maleki in 2016) of the Expectation-Ma…	Curated	Mathematical Methods	`AIMech:GlobalConvergenceOfEMForTwoComponentGaussianMixtures`	4 claims 3 sources
Global Kernel K-Means An incremental kernel clustering algorithm that adds a singleton datum cluster at each stage, runs kernel k-means from each such candidate p…	Curated	Algorithms	`AIMech:GlobalKernelKMeans`	4 claims 1 source
Global Kernel K-Means with Convex Mixture Models aka CMM-Initialized Global Kernel K-Means An incremental kernel clustering algorithm that fits a convex mixture over datum exemplars once, restricts each new-cluster seed search to i…	Curated	Algorithms	`AIMech:ConvexMixtureInitializedGlobalKernelKMeans`	5 claims 1 source
GlobalAveragePooling1D Layer aka GlobalAvgPool1D A pooling layer that performs global average pooling operation for temporal data.	AIO	Layer	`AIO:GlobalAveragePooling1DLayer`	Imported
GlobalAveragePooling2D Layer aka GlobalAvgPool2D A pooling layer that performs global average pooling operation for spatial data.	AIO	Layer	`AIO:GlobalAveragePooling2DLayer`	Imported
GlobalAveragePooling3D Layer aka GlobalAvgPool3D A pooling layer that performs global average pooling operation for 3D data.	AIO	Layer	`AIO:GlobalAveragePooling3DLayer`	Imported
GlobalE and LocalE Entropy-Based Prompt Ordering aka GlobalE and LocalE Prompt Ordering, GlobalE / LocalE Entropy-Based Demonstration Ordering… A validation-free prompt ordering method for few-shot in-context learning that first generates an unlabeled probing set directly from the pr…	Curated	Algorithms	`AIMech:GlobalEAndLocalEEntropyBasedPromptOrdering`	4 claims 3 sources
Globally Convergent Regularization Homotopy and Nyström Newton Method for Generalized Self-Concordant Losses aka Globally Convergent Newton Methods for Ill-Conditioned Generalized Self-Concordant Losses (Marteau-Ferey, Bach, & Rudi 2019), Two-Phase Dikin-Ellipsoid Regularization Continuation Approximate Newton Scheme… Globally Convergent Regularization Homotopy and Nyström Newton Method for Generalized Self-Concordant Losses is a second-order convex optimi…	Curated	Mathematical Methods	`AIMech:GloballyConvergentRegularizationHomotopyAndNystromNewtonForGeneralizedSelfConcordantLosses`	4 claims 3 sources
GlobalMaxPooling1D Layer aka GlobalMaxPool1D A pooling layer that performs global max pooling operation for temporal data.	AIO	Layer	`AIO:GlobalMaxPooling1DLayer`	Imported
GlobalMaxPooling2D Layer aka GlobalMaxPool2D A pooling layer that performs global max pooling operation for spatial data.	AIO	Layer	`AIO:GlobalMaxPooling2DLayer`	Imported
GlobalMaxPooling3D Layer aka GlobalMaxPool3D A pooling layer that performs global max pooling operation for 3D data.	AIO	Layer	`AIO:GlobalMaxPooling3DLayer`	Imported
GloVe aka Global Vectors for Word Representation Word-vector learning from global word co-occurrence statistics.	Curated	Algorithms	`AIMech:GloVe`	1 claim 1 source
GPL (Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval) aka Generative Pseudo Labeling, GPL Unsupervised Domain Adaptation for Dense Retrieval… An unsupervised domain adaptation algorithm for dense text retrieval models that adapts a bi-encoder f_theta to an unlabeled target-domain p…	Curated	Algorithms	`AIMech:GPLGenerativePseudoLabelingForDenseRetrieval`	3 claims 3 sources
Gradient boosting machine aka Gradient boosting, GBM Boosting that adds predictors fitted to negative loss-function gradients.	Curated	Algorithms	`AIMech:GradientBoosting`	1 claim 1 source
Gradient Centralization aka GC, Gradient Centralization Operator… A hyperparameter-free projected-gradient optimization technique for deep neural networks that operates directly on the weight gradient matri…	Curated	Algorithms	`AIMech:GradientCentralizationOptimization`	4 claims 3 sources
Gradient Descent Avoidance of Strict Saddle Points via Stable Manifold Theorem aka Lee-Simchowitz-Jordan-Recht Gradient Descent Converges to Minimizers, Almost-Sure Strict-Saddle Avoidance via Center-Stable Manifold Theorem… Gradient Descent Avoidance of Strict Saddle Points via Stable Manifold Theorem is a dynamical-systems and non-convex optimization analysis i…	Curated	Mathematical Methods	`AIMech:GradientDescentAvoidanceOfStrictSaddlePointsViaStableManifoldTheorem`	3 claims 3 sources
Gradient Masked Averaging for Federated Learning aka FedGMA, Gradient Masked Averaging… A server-side federated aggregation algorithm (FedGMA / GMA; Tenison, Sreeramadas, Mugunthan, Oyallon, Rish, and Belilovsky, TMLR 2023) that…	Curated	Algorithms	`AIMech:FedGmaGradientMaskedAveragingForFederatedLearning`	4 claims 3 sources
Gradient norm clipping aka Global gradient norm clipping A gradient transformation that bounds the Euclidean norm of a chosen joint parameter-gradient vector by uniformly scaling it down to a posit…	Curated	Algorithms	`AIMech:GradientNormClipping`	7 claims 3 sources
Gradient-weighted class activation mapping aka Grad-CAM A convolutional-network localization method weighting activation maps by spatially averaged gradients of a selected target output.	Curated	Algorithms	`AIMech:GradCAM`	1 claim 1 source
GradSkip and GradSkip+ Communication-Accelerated Local Gradient Methods with Gradient Skipping aka GradSkip, GradSkip+… A family of communication-accelerated distributed local gradient methods (GradSkip in Algorithm 2 and its generalized compression-operator f…	Curated	Algorithms	`AIMech:GradSkipAndGradSkipPlusCommunicationAcceleratedLocalGradientMethodsWithGradientSkipping`	4 claims 3 sources
Graph attention network aka GAT A graph neural architecture that updates node representations using learned attention weights over graph neighborhoods.	Curated	Architectures	`AIMech:GraphAttentionNetwork`	1 claim 1 source
Graph attention network v2 aka GATv2 A graph neural architecture whose neighborhood attention scorer applies a learned scalar projection after a nonlinear transformation of the…	Curated	Architectures	`AIMech:GATv2`	1 claim 1 source
Graph Convolutional Network aka GCN A deep neural network that operates directly on graph structures utilizing structural information.	AIO	Network	`AIO:GraphConvolutionalNetwork`	Imported
Graph Convolutional Policy Network aka GPCN A graph convolutional network that generates goal-directed graphs using reinforcement learning and optimizing for rewards and adversarial lo…	AIO	Network	`AIO:GraphConvolutionalPolicyNetwork`	Imported
Graph degree linkage aka GDL, Graph degree linkage clustering An agglomerative clustering algorithm that merges the pair with greatest symmetric graph-degree affinity, formed by summing products of clus…	Curated	Algorithms	`AIMech:GraphDegreeLinkage`	1 claim 1 source
Graph isomorphism network aka GIN A graph neural architecture using multilayer perceptrons on sums of neighboring representations and a separately weighted self-representatio…	Curated	Architectures	`AIMech:GraphIsomorphismNetwork`	1 claim 1 source
Graph Language Model aka Graph LM, Structured representations A language model that operates over structured inputs or outputs represented as graphs enabling reasoning over explicit relational knowledge…	AIO	Model	`AIO:GraphLanguageModel`	Imported
GraphSAGE An inductive graph representation architecture that learns neighborhood aggregation functions to generate node embeddings from features.	Curated	Architectures	`AIMech:GraphSAGE`	1 claim 1 source
GreeDi Two-Stage Distributed Greedy Submodular Maximization aka GreeDi Protocol for Distributed Submodular Maximization, Two-Round MapReduce Greedy Submodular Maximization… GreeDi Two-Stage Distributed Greedy Submodular Maximization is a communication-efficient two-round parallel/MapReduce protocol introduced by…	Curated	Algorithms	`AIMech:GreeDiTwoStageDistributedSubmodularMaximization`	3 claims 3 sources
Greedy best-first search aka GBFS A best-first search algorithm that prioritizes open nodes by a heuristic estimate of remaining cost to a goal, without adding the cost alrea…	Curated	Algorithms	`AIMech:GreedyBestFirstSearch`	2 claims 2 sources
Grid Long Short-Term Memory aka Grid LSTM A neural architecture family whose grid blocks couple hidden representations across computational dimensions while maintaining separate gate…	Curated	Architectures	`AIMech:GridLongShortTermMemory`	6 claims 1 source
Grid Search for Hyperparameter Optimization aka Cartesian Hyperparameter Grid Search A hyperparameter optimization procedure that evaluates a finite Cartesian product of chosen values for each configuration variable and selec…	Curated	Algorithms	`AIMech:GridSearchHyperparameterOptimization`	1 claim 1 source
Grid-search reduction for fair classification aka Agarwal grid-search fairness reduction A fairness-aware classification reduction that evaluates cost-sensitive classifier best responses over a grid of Lagrange-multiplier-derived…	Curated	Algorithms	`AIMech:GridSearchFairClassification`	1 claim 1 source
GRINCH clustering aka Grinch algorithm An incremental hierarchical clustering algorithm that uses set-wise linkage scores to revise a binary cluster tree through local rotations,…	Curated	Algorithms	`AIMech:GRINCHClustering`	6 claims 5 sources
GrIPS Gradient-Free Edit-Based Instruction Search aka GrIPS, Gradient-free Edit-based Instruction Search… A gradient-free discrete prompt optimization algorithm that segments a natural language task instruction into constituent syntactic phrases…	Curated	Algorithms	`AIMech:GrIPSGradientFreeEditBasedInstructionSearch`	4 claims 3 sources
Grothendieck Inequality and Semidefinite Programming for Sparse SBM aka Grothendieck Inequality SDP Analysis for Sparse Stochastic Block Model, Guedon-Vershynin Grothendieck Community Detection Bound… Grothendieck Inequality and Semidefinite Programming for Sparse SBM is an analytical framework introduced by Guedon and Vershynin (2016) for…	Curated	Mathematical Methods	`AIMech:GrothendieckInequalityAndSemidefiniteProgrammingForSparseSBM`	3 claims 3 sources
Group Bias aka In-group Favoritism, In-group bias… A systemic bias characterized by favoring members of one's in-group over out-group members expressed in evaluation resource allocation and o…	AIO	Bias	`AIO:GroupBias`	Imported
Group Restricted Eigenvalue Oracle Inequalities and Multi-Task Group Lasso Minimax Optimality aka Group Restricted Eigenvalue Condition RE(s, c), Multi-Task Group Lasso Oracle Inequalities and Minimax Rate… A non-asymptotic oracle inequality, group support recovery, and minimax optimality framework for Group Lasso and multi-task sparse linear le…	Curated	Mathematical Methods	`AIMech:GroupRestrictedEigenvalueOracleInequalitiesAndMultiTaskGroupLassoMinimaxOptimality`	3 claims 3 sources
Group-topic model aka GT model A probabilistic model family jointly assigning topics to relation-bearing events and topic-specific latent groups to entities, using event t…	Curated	Model Families	`AIMech:GroupTopicModel`	3 claims 1 source
GroupNorm Layer aka GroupNorm A normalization layer that applies Group Normalization over a mini-batch of inputs.	AIO	Layer	`AIO:GroupNormLayer`	Imported
Groupthink Bias aka Groupthink A group bias in which people in a group make non-optimal decisions due to a desire to conform or fear of dissent.	AIO	Bias	`AIO:GroupthinkBias`	Imported
GRU Layer A recurrent layer that implements the Gated Recurrent Unit architecture.	AIO	Layer	`AIO:GRULayer`	Imported
GRUCell Layer A layer that processes one step within the whole time sequence input for a GRU layer.	AIO	Layer	`AIO:GRUCellLayer`	Imported
GSAT A randomized local-search SAT procedure that repeatedly flips a Boolean variable giving the largest change toward more satisfied CNF clauses…	Curated	Algorithms	`AIMech:GSAT`	1 claim 1 source
GSAT averaging-in strategy A GSAT restart-initialization strategy that reuses agreements between earlier complete assignments, randomizes their differing positions, an…	Curated	Algorithms	`AIMech:GSATAveragingIn`	1 claim 1 source
GSAT clause-weighting strategy A GSAT extension that starts each clause with weight one, uses weighted clause counts to select flips, and increases the weights of clauses…	Curated	Algorithms	`AIMech:GSATClauseWeighting`	1 claim 1 source
GSAT with random noise A GSAT variant that mixes a random flip drawn from all formula variables with a globally best GSAT flip, without restricting the random choi…	Curated	Algorithms	`AIMech:GSATWithRandomNoise`	1 claim 1 source
GSAT with random walk aka GWSAT A GSAT variant that mixes a uniformly chosen flip from the distinct variables currently occurring in unsatisfied clauses with a globally bes…	Curated	Algorithms	`AIMech:GSATWithRandomWalk`	2 claims 3 sources
GT-SAGA and GT-SVRG (Decentralized Variance-Reduced Gradient Tracking) aka GT-SAGA and GT-SVRG, GT-SAGA… A unified decentralized finite-sum stochastic optimization framework (GT-VR, Xin, Khan, & Kar 2020, Sections II-III, Algorithms 1-2) for min…	Curated	Algorithms	`AIMech:GtSagaAndGtSvrgDecentralizedVarianceReducedGradientTracking`	4 claims 3 sources
Guarded discrete stochastic network A binary neural constraint-satisfaction architecture whose main assignment neurons are asymmetrically coupled to empty-row guards and update…	Curated	Architectures	`AIMech:GuardedDiscreteStochasticNetwork`	5 claims 2 sources
Guided Fast Local Search A local-search algorithm that combines GLS feature-penalty updates with FLS activation-bit search, reactivating subneighborhoods associated…	Curated	Algorithms	`AIMech:GuidedFastLocalSearch`	5 claims 2 sources
Guided Genetic Algorithm aka GGA The Lau–Tsang genetic-search framework that uses shared adaptive solution-feature penalties both to modify fitness and to construct per-chro…	Curated	Algorithms	`AIMech:GuidedGeneticAlgorithm`	1 claim 2 sources
Guided Grad-CAM A visualization method combining an upsampled Grad-CAM localization map with guided-backpropagation input-space scores.	Curated	Algorithms	`AIMech:GuidedGradCAM`	1 claim 1 source
Guided local search aka GLS A local-search metaheuristic that repeatedly minimizes an objective augmented by feature penalties, increasing selected penalties at local m…	Curated	Algorithms	`AIMech:GuidedLocalSearch`	1 claim 1 source
Gumbel-Softmax relaxation aka Gumbel-Softmax, Concrete distribution… A continuous relaxation of a finite categorical random variable obtained by applying softmax to independent Gumbel-perturbed log weights div…	Curated	Mathematical Methods	`AIMech:GumbelSoftmaxRelaxation`	3 claims 2 sources
Gumbel-Top-k trick aka Gumbel top-k sampling A categorical sampling construction that adds independent standard Gumbel noise to each category’s log weight and returns the indices of the…	Curated	Mathematical Methods	`AIMech:GumbelTopKTrick`	2 claims 2 sources
Gustafson guided-walk Metropolis sampler A continuous-state Metropolis sampler that augments a univariate state with a binary direction, proposes a half-normal displacement along th…	Curated	Algorithms	`AIMech:GustafsonGuidedWalkMetropolis`	5 claims 1 source
HAC-E network clustering aka HAC-E A hierarchical network-clustering variant that greedily guides agglomeration by the observed edge density between two vertex groups and uses…	Curated	Algorithms	`AIMech:HACE`	4 claims 1 source
HAC-ES network clustering aka HAC-ES A hierarchical network-clustering variant that guides agglomeration by the sum of cross-group edge density and Jaccard overlap of the groups…	Curated	Algorithms	`AIMech:HACES`	5 claims 1 source
HAC-ML network clustering aka HAC-ML A greedy network-clustering algorithm that builds a hierarchical stochastic block structure by merging groups with the least loss of profile…	Curated	Algorithms	`AIMech:HACML`	6 claims 1 source
HAC-Q network clustering aka HAC-Q A hierarchical network-clustering variant that uses a degree-corrected modularity contribution to guide group merges and retains hierarchica…	Curated	Algorithms	`AIMech:HACQ`	5 claims 1 source
Hadamard-differentiable threshold functional false discovery proportion central limit theorems and adaptive fixed-point iteration duality aka Neuvial Functional Delta-Method FDP Asymptotics and Threshold Function Framework, Hadamard-Differentiable Threshold Function T(F) = U(F, A(F)) Central Limit Theorem… An asymptotic empirical-process and functional Delta-method framework introduced by Pierre Neuvial (2008, Electronic Journal of Statistics 2…	Curated	Mathematical Methods	`AIMech:HadamardDifferentiableThresholdFDPAsymptoticsAndFixedPointDuality`	4 claims 3 sources
Half-Cauchy combination test aka HCCT, Heavily right Half-Cauchy p-value combination test A statistical p-value combination method that transforms m individual hypothesis test p-values p_1, ..., p_m in (0, 1] into non-negative sta…	Curated	Mathematical Methods	`AIMech:HalfCauchyCombinationTest`	4 claims 2 sources
Halko-Martinsson-Tropp Randomized Subspace Iteration and Low-Rank Matrix Decomposition aka Two-Stage Randomized SVD and QR-Stabilized Subspace Power Iteration, Halko-Martinsson-Tropp Randomized Range Finder and Matrix Approximation Framework A modular two-stage randomized matrix decomposition framework that in Stage A constructs an m x l orthonormal range basis Q (with l = k + p…	Curated	Algorithms	`AIMech:HalkoMartinssonTroppRandomizedSubspaceIterationAndLowRankMatrixDecomposition`	4 claims 3 sources
Hamiltonian Monte Carlo aka HMC, Hybrid Monte Carlo A Markov chain Monte Carlo algorithm for differentiable continuous targets that augments positions with momenta, proposes a state through re…	Curated	Algorithms	`AIMech:HamiltonianMonteCarlo`	2 claims 2 sources
Hammerstein model A real-valued, single-input single-output, discrete-time deterministic nonlinear dynamical model family formed by a memoryless static nonlin…	Curated	Model Families	`AIMech:HammersteinModel`	4 claims 1 source
Hammerstein–Wiener model A real-valued, single-input single-output, discrete-time deterministic dynamical model family formed by a memoryless static input function,…	Curated	Model Families	`AIMech:HammersteinWienerModel`	4 claims 1 source
HAQ (Hardware-Aware Automated Quantization with Mixed Precision) aka HAQ, Hardware-Aware Automated Quantization… HAQ (Hardware-Aware Automated Quantization with Mixed Precision) is an automated mixed-precision neural network quantization framework that…	Curated	Algorithms	`AIMech:HAQHardwareAwareAutomatedQuantizationWithMixedPrecision`	4 claims 3 sources
Hard Sigmoid Function A mathematical function that is a faster approximation of the sigmoid activation using a piecewise linear approximation.	AIO	MathematicalFunction	`AIO:HardSigmoidFunction`	Imported
HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images aka HarmoFL, Harmonizing Local and Global Drifts in Federated Learning… A federated learning algorithm for feature-heterogeneous multi-institution imaging (HarmoFL; Jiang, Wang, and Dou, AAAI 2022) that jointly m…	Curated	Algorithms	`AIMech:HarmoFlHarmonizingLocalAndGlobalDriftsInFederatedLearning`	4 claims 3 sources
HashCRBM A conditional RBM training and prediction method that uses spectral hashing of inputs to retrieve distinct training-output configurations an…	Curated	Algorithms	`AIMech:HashCRBM`	1 claim 2 sources
Hashing Layer A categorical features preprocessing layer which hashes and bins categorical features.	AIO	Layer	`AIO:HashingLayer`	Imported
HAT (Hardware-Aware Transformers for Efficient Natural Language Processing) aka HAT, Hardware-Aware Transformers… HAT (Hardware-Aware Transformers) is a hardware-aware Neural Architecture Search (NAS) framework for sequence-to-sequence encoder-decoder Tr…	Curated	Architectures	`AIMech:HATHardwareAwareTransformersForEfficientNLP`	4 claims 3 sources
HDBSCAN aka Hierarchical DBSCAN Hierarchical density-based clustering that selects clusters across density scales.	Curated	Algorithms	`AIMech:HDBSCAN`	1 claim 1 source
Helmholtz machine A hierarchical probabilistic neural model that pairs a top-down generative model with a separately parameterized bottom-up recognition model…	Curated	Architectures	`AIMech:HelmholtzMachine`	1 claim 2 sources
HeteroFL (Computation and Communication Efficient Federated Learning for Heterogeneous Clients) aka HeteroFL, Heterogeneous Federated Learning via Width-Scaled Subnetworks A system-heterogeneous federated learning framework (Diao, Ding, & Tarokh 2021, Section 3, Equations 1-4, Algorithm 1) that allocates nested…	Curated	Algorithms	`AIMech:HeteroFlWidthScaledSubnetworkAggregationForHeterogeneousFederatedLearning`	4 claims 3 sources
HeteroPCA Iterative Diagonal Imputation and Robust Subspace Perturbation for Heteroskedastic PCA aka HeteroPCA, Heteroskedastic Principal Component Analysis via Iterative Diagonal Imputation… An iterative spectral estimation algorithm and deterministic subspace perturbation framework (introduced by Anru R. Zhang, T. Tony Cai, and…	Curated	Algorithms	`AIMech:HeteroPCAIterativeDiagonalImputationAndRobustSubspacePerturbationForHeteroskedasticPCA`	3 claims 3 sources
Heteroskedastic PCA Principal Subspace Confidence Regions and Spiked Covariance Inference with Missing Data aka Diagonal-Deleted Heteroskedastic PCA Subspace Inference with Missing Data, Yan-Chen-Fan Heteroskedastic PCA Confidence Regions and Spiked Covariance Inference… A distributional inference and uncertainty quantification methodology (introduced by Yuling Yan, Yuxin Chen, and Jianqing Fan in 2024) for e…	Curated	Mathematical Methods	`AIMech:HeteroskedasticPCAPrincipalSubspaceConfidenceRegionsAndSpikedCovarianceInferenceWithMissingData`	3 claims 3 sources
Heuristic tree sampling aka Chen heuristic sampling A randomized estimator of additive properties of an implicit rooted tree that processes ordered strata using one sampled representative and…	Curated	Algorithms	`AIMech:HeuristicTreeSampling`	5 claims 2 sources
HIBERT (Hierarchical Bidirectional Transformers for Document Summarization) aka HIBERT, Hierarchical Bidirectional Transformers for Document Summarization… A hierarchical bidirectional Transformer document encoding and pre-training framework (Zhang, Wei, & Zhou, ACL 2019) that stacks a word-leve…	Curated	Architectures	`AIMech:HIBERTHierarchicalBidirectionalTransformersForDocumentSummarization`	4 claims 3 sources
Hidden Layer A layer located between the input and output that performs nonlinear transformations of the inputs entered into the network.	AIO	Layer	`AIO:HiddenLayer`	Imported
Hidden Markov decision tree aka HMDT A conditional latent sequence-model family that extends a probabilistic hierarchical decision tree by coupling each decision level to the sa…	Curated	Model Families	`AIMech:HiddenMarkovDecisionTree`	1 claim 1 source
Hidden Markov model aka HMM A sequence model whose hidden Markov states generate observations through state-dependent emission distributions.	Curated	Model Families	`AIMech:HiddenMarkovModel`	1 claim 1 source
Hidden Markov model with auxiliary memory aka Auxiliary-memory context-sensitive hidden Markov model A hidden-state symbol-sequence model family in which paired states write emitted symbols to auxiliary memory and later read them to conditio…	Curated	Model Families	`AIMech:HiddenMarkovModelWithAuxiliaryMemory`	1 claim 1 source
Hidden Markov random field aka HMRF, Hidden Markov field A latent-variable graphical-model family whose unobserved label field has the Markov property on a specified neighborhood graph, with observ…	Curated	Model Families	`AIMech:HiddenMarkovRandomField`	1 claim 1 source
Hidden Markov tree aka HMT A latent-variable model on a fixed rooted tree in which hidden states factor into a root distribution and conditionally independent parent-t…	Curated	Model Families	`AIMech:HiddenMarkovTree`	1 claim 1 source
Hidden semi-Markov model aka HSMM, Explicit-duration hidden Markov model… A latent-state sequence-model family that assigns explicit distributions to state sojourn durations, with state changes governed by an embed…	Curated	Model Families	`AIMech:HiddenSemiMarkovModel`	1 claim 1 source
Hidden–observed pair Markov random field aka Pairwise hidden–observed Markov field A latent-variable spatial-model family in which each site contains a hidden label and an observation, and their joint paired field has a nor…	Curated	Model Families	`AIMech:HiddenObservedPairMarkovRandomField`	1 claim 1 source
Hierarchical Classification A classification focused on methods that group things according to a hierarchy.	AIO	MachineLearningTask	`AIO:HierarchicalClassification`	Imported
Hierarchical Clustering aka HCL A clustering that builds a hierarchy of clusters.	AIO	MachineLearningTask	`AIO:HierarchicalClustering`	Imported
Hierarchical harmonium aka HH A labeled harmonium model family coupling binary words, Gaussian image features and binary category indicators to shared Gaussian latent var…	Curated	Model Families	`AIMech:HierarchicalHarmonium`	3 claims 1 source
Hierarchical Language Model aka Hierarchical LM, multi-scale representations A language model that represents language at multiple levels of granularity learning hierarchical representations that capture both low-leve…	AIO	Model	`AIO:HierarchicalLanguageModel`	Imported
Hierarchical log-bilinear language model aka HLBL A next-word language architecture that computes one linear context feature vector and uses its dot products with internal-node vectors to as…	Curated	Architectures	`AIMech:HierarchicalLogBilinearLanguageModel`	1 claim 1 source
Hierarchical mixture of experts aka HME A conditional mixture-model family that organizes output experts as leaves of a tree and forms each leaf’s mixture weight by multiplying inp…	Curated	Model Families	`AIMech:HierarchicalMixtureOfExperts`	1 claim 1 source
Hierarchical pachinko allocation model aka hPAM A pachinko topic-model family that associates word-emission distributions with internal topic nodes as well as terminal topics, allowing doc…	Curated	Model Families	`AIMech:HierarchicalPachinkoAllocationModel`	3 claims 1 source
Hierarchical probabilistic neural network language model A neural next-word architecture that factors word probabilities along a binary vocabulary tree and shares a nonlinear branch predictor condi…	Curated	Architectures	`AIMech:HierarchicalProbabilisticNeuralNetworkLanguageModel`	1 claim 1 source
Hierarchical softmax A neural categorical-output component that assigns a probability to each vocabulary leaf by multiplying normalized branch probabilities alon…	Curated	Layers & Modules	`AIMech:HierarchicalSoftmax`	1 claim 3 sources
High-Dimensional Covariance Estimation by Minimizing L1-Penalized Log-Determinant Divergence aka L1-Penalized Log-Determinant Bregman Divergence Precision Matrix Estimation, High-Dimensional Graphical Lasso Primal-Dual Witness Analysis… High-Dimensional Covariance Estimation by Minimizing L1-Penalized Log-Determinant Divergence is a convex M-estimation and primal-dual witnes…	Curated	Mathematical Methods	`AIMech:HighDimensionalCovarianceEstimationByL1PenalizedLogDeterminantDivergence`	3 claims 3 sources
High-Dimensional Covariance Regularization by Hard Thresholding aka Bickel-Levina Hard-Thresholded Sample Covariance Estimator, Operator-Norm Consistent Hard-Thresholding Covariance Regularization… A permutation-invariant high-dimensional covariance estimation and tuning-selection methodology that applies the entrywise hard-thresholding…	Curated	Mathematical Methods	`AIMech:HighDimensionalCovarianceRegularizationByHardThresholding`	3 claims 3 sources
High-Dimensional Gaussian Graphical Model Neighborhood Selection with the Lasso aka Meinshausen-Buhlmann Neighborhood Selection, Lasso Gaussian Graphical Model Neighborhood Selection… High-Dimensional Gaussian Graphical Model Neighborhood Selection with the Lasso is a nodewise L1-penalized regression method (Meinshausen &…	Curated	Mathematical Methods	`AIMech:HighDimensionalGaussianGraphicalModelNeighborhoodSelectionWithTheLasso`	3 claims 3 sources
High-Dimensional Ising Model Selection via L1-Regularized Logistic Regression aka High-Dimensional Ising Model Selection Using l_1-Regularized Logistic Regression (Ravikumar, Wainwright, & Lafferty 2010), High-Dimensional Graphical Model Selection Using l_1-Regularized Logistic Regression… High-Dimensional Ising Model Selection via L1-Regularized Logistic Regression is a nodewise convex pseudo-likelihood graphical model structu…	Curated	Mathematical Methods	`AIMech:HighDimensionalIsingModelSelectionViaL1RegularizedLogisticRegression`	3 claims 3 sources
High-order polynomial projection operators aka HiPPO (polynomial projection) A family of time-dependent operators that represents a signal's past by coefficients of its optimal finite-dimensional polynomial approximat…	Curated	Mathematical Methods	`AIMech:HiPPOProjection`	1 claim 1 source
Hill climbing aka Hill-climbing search, Greedy local search A family of local-improvement search procedures that replaces a current solution with a strictly better neighbor and stops when no improving…	Curated	Algorithms	`AIMech:HillClimbing`	1 claim 2 sources
Historical Bias A bias characterized by long-standing biases encoded in society over time distinct from biases in historical description or interpretation.	AIO	Bias	`AIO:HistoricalBias`	Imported
HITS hub and authority ranking aka HITS A link-analysis ranking algorithm that constructs a query-focused directed page graph and alternately propagates authority scores from incom…	Curated	Algorithms	`AIMech:HITSRanking`	5 claims 1 source
Hitting-Set IP Relaxation and Tiled Interval Cover for Paging with Time Windows and Delays aka PageTW and PageD Hitting-Set IP Caching Algorithm, Right-and-Double-Extension Hitting-Set LP for Caching with Deadlines… An online and offline approximation framework for weighted paging with request time windows (PageTW) and monotone delay penalties (PageD) on…	Curated	Algorithms	`AIMech:HittingSetIPAndTiledIntervalCoverOnlinePagingWithTimeWindowsAndDelays`	4 claims 3 sources
HLATR Hybrid List Aware Transformer Reranking aka HLATR, Hybrid List Aware Transformer Reranking… A lightweight list-aware neural reranking architecture for multi-stage text retrieval that couples coarse first-stage retrieval features wit…	Curated	Architectures	`AIMech:HLATRHybridListAwareTransformerReranking`	4 claims 3 sources
Holland bucket-brigade credit assignment A classifier-system credit-assignment procedure in which satisfied condition/action rules compete using strength-and-specificity bids, winni…	Curated	Algorithms	`AIMech:HollandBucketBrigade`	5 claims 1 source
Hopfield Network aka HN, Ising model of a neural network… A symmetrically connected network that is a type of recurrent artificial neural network serving as a content-addressable memory system.	AIO	Network	`AIO:HopfieldNetwork`	Imported
Hostile Attribution Bias A use and interpretation bias where individuals perceive benign or ambiguous behaviors as hostile.	AIO	Bias	`AIO:HostileAttributionBias`	Imported
HRSAT A source-scoped SAT-search algorithm described by the literal composition of the 1995 GenSAT stages: a probability-controlled choice between…	Curated	Algorithms	`AIMech:HRSAT`	5 claims 2 sources
HSAT A GSAT variant that breaks ties among best-scoring variable flips by choosing the variable flipped least recently in the current attempt, us…	Curated	Algorithms	`AIMech:HSAT`	1 claim 1 source
Huber-robust heavy-tailed confidence sequences aka Huber-Robust Confidence Sequence, TV-Contaminated Heavy-Tailed Robust Confidence Sequence… A family of nonasymptotic, anytime-valid sequential confidence sequences (Wang & Ramdas 2023, AISTATS / PMLR 206:9662–9679) for the mean mu(…	Curated	Mathematical Methods	`AIMech:HuberRobustHeavyTailedConfidenceSequences`	4 claims 3 sources
Human Bias A bias in human thought based on heuristic principles leading to simplified judgmental operations.	AIO	Bias	`AIO:HumanBias`	Imported
Human Reporting Bias An individual bias that arises when users depend on automated systems as heuristic substitutes for their own information-seeking and process…	AIO	Bias	`AIO:HumanReportingBias`	Imported
Hungry Hungry Hippos layer aka H3 A sequence layer that combines projected queries, keys and values with shift and diagonal state-space models, using multiplicative interacti…	Curated	Layers & Modules	`AIMech:H3Layer`	1 claim 1 source
Hutchinson Stochastic Diagonal Estimator aka Hutchinson Diagonal Estimator, Hutchinsons Diagonal Estimator… A randomized matrix-free numerical linear algebra method that estimates the diagonal vector diag(A) of a square matrix A using only implicit…	Curated	Mathematical Methods	`AIMech:HutchinsonsStochasticDiagonalEstimator`	4 claims 3 sources
HyDE Hypothetical Document Embeddings aka HyDE, Hypothetical Document Embeddings… A training-free zero-shot dense retrieval method that decomposes relevance modeling into an instruction-following natural language generatio…	Curated	Algorithms	`AIMech:HyDEHypotheticalDocumentEmbeddings`	4 claims 3 sources
HydraLoRA aka Hydra Low-Rank Adaptation, Asymmetric Shared-A Multi-B Mixture-of-Experts LoRA… An asymmetric parameter-efficient low-rank adaptation architecture that pairs a single shared low-rank down-projection matrix A with multipl…	Curated	Architectures	`AIMech:HydraLoRA`	4 claims 3 sources
Hyperband A hyperparameter resource-allocation algorithm that runs successive-halving brackets with different initial configuration counts and startin…	Curated	Algorithms	`AIMech:Hyperband`	1 claim 1 source
Hyperdecoder (Encoder-Conditioned Instance-Specific Decoder Adapter Hypernetwork) aka Hyperdecoder, Hyperdecoders… A parameter-efficient multi-task encoder-decoder Transformer architecture that places shared trainable parallel adapters in the frozen encod…	Curated	Architectures	`AIMech:HyperdecoderInstanceSpecificDecoderAdapter`	4 claims 3 sources
HyperFormer (Shared Hypernetwork Multi-Task Adapter) aka HyperFormer, HyperFormer++… A parameter-efficient multi-task Transformer adaptation architecture that learns low-dimensional task, layer-ID, and adapter-position embedd…	Curated	Architectures	`AIMech:HyperFormerSharedHypernetworkAdapter`	4 claims 3 sources
HyperGrid (Grid-wise Decomposable Hyper Projections for Multi-Task Transformers) aka HyperGrid, HyperGrid Transformer… A multi-task Transformer projection architecture that pools the sequence task-prefix token into X in R^{d_m}, forms a d_r x d_c gating matri…	Curated	Architectures	`AIMech:HyperGridDecomposableGridwiseHyperProjection`	4 claims 3 sources
HyperPrompt (HyperNetwork-Generated Task-Conditioned Self-Attention Prompts) aka HyperPrompt, HyperPrompt-Global… A multi-task Transformer architecture that initializes a trainable global task prompt P_tau in R^{l x d} for each task tau and applies local…	Curated	Architectures	`AIMech:HyperPromptTaskConditionedAttentionPrompt`	4 claims 3 sources
IA3 Activation Rescaling aka IA3, Infused Adapter by Inhibiting and Amplifying Inner Activations A transformer adaptation method that learns task-specific vectors to rescale attention key/value channels and intermediate feedforward activ…	Curated	Algorithms	`AIMech:IA3ActivationRescaling`	5 claims 2 sources
ID3 aka Iterative Dichotomiser 3 Decision-tree induction that selects categorical attributes by information gain.	Curated	Algorithms	`AIMech:ID3`	1 claim 1 source
IDA* with an Incremental Model aka IDA*IM An iterative-deepening heuristic search algorithm that learns a conditional model of search-tree cost increments, predicts later cost thresh…	Curated	Algorithms	`AIMech:IDAStarIncrementalModel`	5 claims 1 source
Identity-initialized rectified recurrent neural network aka IRNN A recurrent neural sequence architecture using rectified linear hidden units, zero initial recurrent biases, and a trainable recurrent matri…	Curated	Architectures	`AIMech:IdentityInitializedRecurrentNeuralNetwork`	6 claims 1 source
IECO constrained elliptical-mixture classification A constrained classification procedure that models each known class by a mixture of elliptical category distributions, marginalizes category…	Curated	Algorithms	`AIMech:IECOConstrainedMixtureClassification`	5 claims 3 sources
IHSAT A GenSAT variant that chooses the least recently flipped variable among all flips that do not decrease the satisfied-clause count, or among…	Curated	Algorithms	`AIMech:IHSAT`	1 claim 1 source
Image Augmentation Layer A layer that performs image data preprocessing augmentations.	AIO	Layer	`AIO:ImageAugmentationLayer`	Imported
Image Preprocessing Layer A layer that performs image data preprocessing operations.	AIO	Layer	`AIO:ImagePreprocessingLayer`	Imported
Implicit Bias aka Confirmatory Bias An individual bias characterized by unconscious beliefs attitudes feelings associations or stereotypes that affect information processing de…	AIO	Bias	`AIO:ImplicitBias`	Imported
Implicit Language Model aka Implicit LM, Energy-based models… A language model that uses an energy function to score entire sequences instead of factorizing probabilities autoregressively better capturi…	AIO	Model	`AIO:ImplicitLanguageModel`	Imported
Implicit Regularization in Nonconvex Statistical Estimation by Leave-One-Out Trajectory Analysis aka Implicit Regularization of Vanilla Gradient Descent in Nonconvex Estimation, Ma-Wang-Chi-Chen Leave-One-Out Nonconvex Trajectory Analysis… A general nonconvex optimization and statistical estimation analysis framework (introduced by Cong Ma, Kaizheng Wang, Yuejie Chi, and Yuxin…	Curated	Mathematical Methods	`AIMech:ImplicitRegularizationInNonconvexStatisticalEstimationByLeaveOneOutTrajectoryAnalysis`	3 claims 3 sources
Improved consistency training aka iCT (consistency training) The consistency-model training procedure of Song and Dhariwal that learns directly from paired shared-noise data perturbations using a stop-…	Curated	Algorithms	`AIMech:ImprovedConsistencyTraining`	1 claim 1 source
Improved limited discrepancy search aka ILDS Korf’s discrepancy-search variant that uses a supplied maximum search depth and remaining discrepancy count to generate each path to that de…	Curated	Algorithms	`AIMech:ImprovedLimitedDiscrepancySearch`	2 claims 2 sources
Improved Variational Online Newton (IVON) aka IVON, Improved Variational Online Newton… Improved Variational Online Newton (IVON) is a scalable variational Bayesian learning algorithm for deep neural networks that optimizes a di…	Curated	Algorithms	`AIMech:IvonImprovedVariationalOnlineNewtonForLargeDeepNetworks`	4 claims 3 sources
Incremental Expectation Maximization aka Incremental EM, IEM (incremental expectation maximization) An EM variant for independent observed cases that refreshes selected cached case posteriors at the current parameters and then fits paramete…	Curated	Algorithms	`AIMech:IncrementalExpectationMaximization`	4 claims 2 sources
Incremental Few-shot Learning aka IFSL A deep neural network trained on a base set of classes and then presented with novel classes, each with few labeled examples.	AIO	Network	`AIO:IncremenetalFewshotLearning`	Imported
Independence Metropolis–Hastings sampling aka Independence Metropolis sampler, IMH A Metropolis–Hastings sampler whose proposal distribution is fixed independently of the current state, with proposal-density ratios still in…	Curated	Algorithms	`AIMech:IndependenceMetropolisHastings`	1 claim 1 source
Individual Bias A bias characterized by a persistent point of view or limited list of such points of view, applied by an individual.	AIO	Bias	`AIO:IndividualBias`	Imported
Infomax Independent Component Analysis aka Infomax ICA, Bell-Sejnowski ICA An unsupervised source-separation learning algorithm that adjusts an invertible square linear transform and biases by the ordinary gradient…	Curated	Algorithms	`AIMech:InfomaxICA`	3 claims 1 source
InfoNCE aka InfoNCE loss A contrastive log-softmax objective that identifies a joint positive among sampled candidates and, under independent marginal-negative sampl…	Curated	Mathematical Methods	`AIMech:InfoNCE`	1 claim 2 sources
Information maximizing self-augmented training aka IMSAT, Information maximising self-augmented training A discrete representation-learning procedure that combines self-augmentation consistency with an information objective, using categorical ou…	Curated	Algorithms	`AIMech:InformationMaximizingSelfAugmentedTraining`	1 claim 4 sources
Information-geometric optimization A stochastic black-box optimization framework that adapts a parametrized sampling distribution using objective ranks and Fisher natural grad…	Curated	Algorithms	`AIMech:InformationGeometricOptimization`	6 claims 1 source
Information-Theoretic Limits of High-Dimensional Binary Graphical Model Selection aka Information-Theoretic Limits of Selecting Binary Graphical Models in High Dimensions, Santhanam-Wainwright Ising Graphical Model Selection Capacity… Information-Theoretic Limits of High-Dimensional Binary Graphical Model Selection is a minimax information-theoretic framework (Santhanam &…	Curated	Mathematical Methods	`AIMech:InformationTheoreticLimitsOfHighDimensionalBinaryGraphicalModelSelection`	3 claims 3 sources
Information-Theoretic Limits of High-Dimensional Noisy Sparsity Recovery aka Information-Theoretic Limits on Sparsity Recovery in the High-Dimensional and Noisy Setting (Wainwright 2009), Optimal Subset-Projection Decoder and Fano Multiway Lower Bounds for Noisy Support Recovery… Information-Theoretic Limits of High-Dimensional Noisy Sparsity Recovery is an information-theoretic and optimal subset-projection decoding…	Curated	Mathematical Methods	`AIMech:InformationTheoreticLimitsOfHighDimensionalNoisySparsityRecovery`	3 claims 3 sources
Informed backtracking repair A finite-CSP repair-oriented backtracking controller that uses an existing complete assignment to order repairs while recursively extending…	Curated	Algorithms	`AIMech:InformedBacktrackingRepair`	5 claims 1 source
Informed NegaScout An adversarial game-tree search procedure that augments NegaScout’s minimal-window traversal with recursively retained information from an i…	Curated	Algorithms	`AIMech:InformedNegaScout`	6 claims 1 source
Inherited Bias A processing bias arising when machine learning applications generate inputs for other machine learning algorithms passing on any existing b…	AIO	Bias	`AIO:InheritedBias`	Imported
INLA group node conflict diagnostic A group-wise Bayesian model diagnostic for latent Gaussian models that uses two INLA fits per selected group to compare remaining-data and w…	Curated	Algorithms	`AIMech:INLAGroupNodeConflictDiagnostic`	7 claims 8 sources
InPars In-Context Data Augmentation for Information Retrieval aka InPars, Inquisitive Parrots for Search… A few-shot synthetic data augmentation method for information retrieval (Inquisitive Parrots for Search) that prompts a pretrained language…	Curated	Algorithms	`AIMech:InParsInContextDataAugmentationForInformationRetrieval`	4 claims 3 sources
Input Layer A layer composed of artificial input neurons that brings the initial data into the system for further processing by subsequent layers.	AIO	Layer	`AIO:InputLayer`	Imported
Input-output hidden Markov model aka IOHMM, Input-output HMM A conditional latent sequence-model family whose discrete hidden-state transitions and state-specific observation distributions depend on th…	Curated	Model Families	`AIMech:InputOutputHiddenMarkovModel`	1 claim 1 source
InputLayer Layer A layer to be used as an entry point into a Network (a graph of layers).	AIO	Layer	`AIO:InputLayerLayer`	Imported
InputSpec Layer A layer that specifies the rank, dtype and shape of every input to a layer.	AIO	Layer	`AIO:InputSpecLayer`	Imported
Instance-Dependent Prompt Generation aka IDPG, M-IDPG-PHM… A conditional parameter-efficient prompt-tuning method for pre-trained language models that generates continuous soft prompts W_p(T, x_i) =…	Curated	Algorithms	`AIMech:IDPGInstanceDependentPromptGeneration`	4 claims 3 sources
InstanceNorm1D Layer aka InstanceNorm1D A normalization layer that applies Instance Normalization over a 2D (unbatched) or 3D (batched) input.	AIO	Layer	`AIO:InstanceNorm1DLayer`	Imported
InstanceNorm2D A normalization layer that applies Instance Normalization over a 4D input (a mini-batch of 2D inputs with additional channel dimension).	AIO	Layer	`AIO:InstanceNorm2D`	Imported
InstanceNorm3D Layer aka InstanceNorm3D A normalization layer that applies Instance Normalization over a 5D input (a mini-batch of 3D inputs with additional channel dimension).	AIO	Layer	`AIO:InstanceNorm3DLayer`	Imported
Institutional Bias A systemic bias exhibited at the level of entire institutions where practices or norms result in the favoring or disadvantaging of certain s…	AIO	Bias	`AIO:InstitutionalBias`	Imported
Instruction-Tuned LLM aka Instruction-Tuned Large Language Model, constitutional AI… A large language model which is fine-tuned to follow natural language instructions accurately and safely, learning to map from instructions…	AIO	Model	`AIO:InstructionTunedLLM`	Imported
IntegerLookup Layer A categorical features preprocessing layer that maps integer features to contiguous ranges.	AIO	Layer	`AIO:IntegerLookupLayer`	Imported
Integrated gradients aka IG A feature-attribution method that integrates a prediction's input gradients along the straight path from a chosen baseline to the input.	Curated	Mathematical Methods	`AIMech:IntegratedGradients`	1 claim 1 source
Interaction Network aka Interaction Networks, IN (interaction network) A graph-based neural architecture that applies a shared relation model to supplied directed attributed object relations, sums predicted effe…	Curated	Architectures	`AIMech:InteractionNetwork`	6 claims 1 source
Interpolated variational information bound aka I-alpha bound, Nonlinearly interpolated mutual information lower bound A family of multi-sample mutual-information lower bounds that interpolates the critic’s empirical partition estimate with a positive variati…	Curated	Mathematical Methods	`AIMech:InterpolatedVariationalInformationBound`	3 claims 3 sources
Interpolation consistency training aka ICT A semi-supervised training procedure that encourages a student’s prediction at an interpolated pair of unlabeled inputs to match the same in…	Curated	Algorithms	`AIMech:InterpolationConsistencyTraining`	1 claim 1 source
Interpretation Bias An individual bias where users interpret algorithmic outputs according to their internalized biases and views.	AIO	Bias	`AIO:InterpretationBias`	Imported
Invariant information clustering aka IIC A neural clustering procedure that maximizes mutual information between discrete cluster-assignment variables for paired unlabeled samples,…	Curated	Algorithms	`AIMech:InvariantInformationClustering`	1 claim 2 sources
Inverse compositional spatial transformer network A recurrent learned image-alignment architecture that repeatedly applies one shared geometric predictor to the original source sampled at th…	Curated	Architectures	`AIMech:InverseCompositionalSpatialTransformerNetwork`	5 claims 1 source
IPOP-CMA-ES The original increasing-population restart CMA-ES algorithm, which independently restarts its weighted, rank-mu covariance-matrix-adaptation…	Curated	Algorithms	`AIMech:IPOPCMAES`	6 claims 4 sources
Isomap aka Isometric Feature Mapping A nonlinear dimensionality-reduction algorithm that estimates manifold geodesic distances by shortest paths in a local neighborhood graph an…	Curated	Algorithms	`AIMech:Isomap`	2 claims 2 sources
Iterated conditional modes aka ICM A deterministic conditional-mode optimization algorithm that repeatedly updates one variable to a mode of its conditional distribution given…	Curated	Algorithms	`AIMech:IteratedConditionalModes`	2 claims 2 sources
Iterated local search aka ILS A metaheuristic that builds a single search trajectory among solutions returned by an embedded optimizer by perturbing the current accepted…	Curated	Algorithms	`AIMech:IteratedLocalSearch`	1 claim 1 source
Iterated Wiener Filter aka IWF An iterative MAP image-denoising algorithm that majorizes a fixed Product of Student-t log-potential and alternates response-dependent preci…	Curated	Algorithms	`AIMech:IteratedWienerFilter`	3 claims 1 source
Iterative Bregman Projections and Bregman-Dykstra Regularized Optimal Transport aka Iterative Bregman Projections (IBP) for Optimal Transport, Bregman-Dykstra Algorithm for Constrained Regularized Transport… Iterative Bregman Projections and Bregman-Dykstra Regularized Optimal Transport is a convex-analytic optimization framework introduced by Be…	Curated	Algorithms	`AIMech:IterativeBregmanProjectionsAndBregmanDykstraRegularizedOptimalTransport`	3 claims 3 sources
Iterative broadening A tree-search strategy that repeats depth-first search with increasing limits on the number of ordered successors considered at each parent,…	Curated	Algorithms	`AIMech:IterativeBroadening`	5 claims 1 source
Iterative conditional estimation aka ICE An incomplete-data parameter-estimation procedure that repeatedly replaces a chosen complete-data estimator by its conditional expectation g…	Curated	Algorithms	`AIMech:IterativeConditionalEstimation`	1 claim 2 sources
Iterative expansion A recursive heuristic tree-search procedure that repeatedly explores a lowest-valued child within a bound set by its caller and competing ch…	Curated	Algorithms	`AIMech:IterativeExpansion`	6 claims 2 sources
Iterative Federated Clustering Algorithm (IFCA) aka IFCA, Iterative Federated Clustering Algorithm… An alternating minimization framework for clustered federated learning (IFCA, Algorithm 2) over m clients partitioned into k unknown latent…	Curated	Algorithms	`AIMech:IfcaIterativeFederatedClusteringAlgorithm`	4 claims 3 sources
Iterative Hard Thresholding for Compressed Sensing aka Iterative Hard Thresholding, IHT for Compressed Sensing… Iterative Hard Thresholding for Compressed Sensing (IHT) is a first-order non-convex projected gradient algorithm analyzed by Blumensath and…	Curated	Algorithms	`AIMech:IterativeHardThresholdingForCompressedSensing`	3 claims 3 sources
Iterative Hessian Sketch for Constrained Least-Squares and Information-Theoretic Classical Sketching Lower Bounds aka Iterative Hessian Sketch (IHS, Pilanci & Wainwright 2016), Hessian Sketch for Constrained Least-Squares… Iterative Hessian Sketch for Constrained Least-Squares and Information-Theoretic Classical Sketching Lower Bounds is a randomized sketching…	Curated	Mathematical Methods	`AIMech:IterativeHessianSketchForConstrainedLeastSquares`	3 claims 3 sources
Iterative linear best-first search aka ILBFS An iterative organization of best-first tree search that explicitly retains a principal path and its immediate children, eagerly collapses a…	Curated	Algorithms	`AIMech:IterativeLinearBestFirstSearch`	6 claims 1 source
Iterative Product Quantization for Neural Networks (And the Bit Goes Down / Activation-Weighted PQ) aka Iterative Product Quantization for Neural Networks, And the Bit Goes Down Activation-Weighted Product Quantization… Iterative Product Quantization for Neural Networks (introduced in 'And the Bit Goes Down: Revisiting the Quantization of Neural Networks', o…	Curated	Algorithms	`AIMech:AndTheBitGoesDownIterativeProductQuantizationForNeuralNetworks`	4 claims 3 sources
Iterative threshold search A limited-memory heuristic tree-search algorithm that explores branches within an iteratively revised cost threshold, stores bounds for bran…	Curated	Algorithms	`AIMech:IterativeThresholdSearch`	4 claims 1 source
Iterative weakening A policy for selecting a sufficient search bias by trying a fixed family of search-space restrictions in increasing order of known evaluatio…	Curated	Algorithms	`AIMech:IterativeWeakening`	5 claims 1 source
Iterative-deepening A-star search aka IDA, Iterative-deepening-A A heuristic search algorithm that repeats depth-first passes bounded by f=g+h, starting with the start-state heuristic and raising each cuto…	Curated	Algorithms	`AIMech:IterativeDeepeningAStar`	2 claims 2 sources
ITERSSS* A memory-bounded solution-tree search algorithm for minimax evaluation of a finite uniform alternating game tree that controls an SSS*-style…	Curated	Algorithms	`AIMech:ITERSSSStar`	9 claims 1 source
Joint term-citation model A latent-factor document model that shares each document's fixed topic proportions between categorical term and citation-incidence channels,…	Curated	Model Families	`AIMech:JointTermCitationModel`	2 claims 1 source
Joint unsupervised learning of deep representations and image clusters aka JULE, Joint unsupervised learning An image representation and clustering procedure that alternates periods of graph-based agglomerative merging with convolutional-network upd…	Curated	Algorithms	`AIMech:JointUnsupervisedLearning`	1 claim 2 sources
Jumping Knowledge network aka JK-Net, Jumping Knowledge networks A graph neural architecture that sends intermediate node representations from multiple neighborhood-aggregation depths to a final layer-aggr…	Curated	Architectures	`AIMech:JumpingKnowledgeNetwork`	1 claim 1 source
K-BFGS and K-BFGS(L) (Kronecker-Factored Quasi-Newton Optimization) aka K-BFGS, K-BFGS(L)… A stochastic Kronecker-factored quasi-Newton optimization method for deep neural networks that approximates each layer's block-diagonal inve…	Curated	Algorithms	`AIMech:KBfgsKroneckerFactoredQuasiNewtonOptimization`	5 claims 3 sources
K-Bounded CoPE scheduling An execution-focused CoPE scheduling schema that enumerates placements of a bounded prefix of each candidate action head, completes the rema…	Curated	Algorithms	`AIMech:KBoundedCoPE`	4 claims 1 source
k-Determinantal Point Processes for Fixed-Size Subset Selection aka k-DPP (Fixed-Size Determinantal Point Process), Kulesza-Taskar Cardinality-Conditioned Determinantal Point Process… k-Determinantal Point Processes for Fixed-Size Subset Selection (k-DPPs) is a probabilistic diverse subset selection model and exact polynom…	Curated	Mathematical Methods	`AIMech:KDeterminantalPointProcessesForFixedSizeSubsetSelection`	3 claims 3 sources
k-means Clustering that partitions observations around centroids by minimizing within-cluster squared distances.	Curated	Algorithms	`AIMech:KMeans`	1 claim 1 source
K-nearest Neighbor Algorithm aka K-NN, KNN A machine learning task that groups objects by a plurality vote of its neighbors, assigning each object to the class most common among its k…	AIO	MachineLearningTask	`AIO:KnearestNeighborAlgorithm`	Imported
K-nearest Neighbor Classification Algorithm aka K-NN Classification, KNN Classification A classification and clustering that classifies objects by a plurality vote of its neighbors, assigning each object to the class most common…	AIO	MachineLearningTask	`AIO:KnearestNeighborClassificationAlgorithm`	Imported
K-nearest Neighbor Regression Algorithm aka K-NN Regression, KNN Regression A regression analysis that assigns the average of the values of k nearest neighbors to objects.	AIO	MachineLearningTask	`AIO:KnearestNeighborRegressionAlgorithm`	Imported
K-SVD A dictionary-learning algorithm that alternates sparse coding of training samples with sequential updates of each dictionary atom and its ac…	Curated	Algorithms	`AIMech:KSVD`	6 claims 1 source
KADABRA adaptive betweenness approximation aka KADABRA, KADABRA all-node adaptive betweenness approximation An adaptive sampling algorithm for static-graph betweenness that averages internal-node indicators of uniformly sampled shortest paths and s…	Curated	Algorithms	`AIMech:KADABRAAdaptiveBetweenness`	6 claims 2 sources
KADABRA balanced bidirectional shortest-path sampling aka KADABRA balanced bidirectional BFS sampler, KADABRA shortest-path sampler A shortest-path sampling algorithm that expands complete breadth-first-search frontiers from opposite endpoints according to frontier edge v…	Curated	Algorithms	`AIMech:KADABRABalancedBidirectionalPathSampling`	6 claims 2 sources
Kardam Lipschitz- and Frequency-Filtered Asynchronous Byzantine Stochastic Gradient Descent aka Kardam, Kardam Asynchronous Byzantine SGD… A Byzantine-resilient asynchronous stochastic gradient descent algorithm proposed by Damaskinos, El Mhamdi, Guerraoui, Patra, and Taziki (IC…	Curated	Algorithms	`AIMech:KardamLipschitzAndFrequencyFilteredAsynchronousByzantineStochasticGradientDescent`	4 claims 3 sources
Karmarkar–Karp differencing aka Karmarkar–Karp heuristic A two-way number-partitioning heuristic that repeatedly replaces the two largest remaining nonnegative residuals by their difference, then r…	Curated	Algorithms	`AIMech:KarmarkarKarpDifferencing`	6 claims 2 sources
KATE kNN-Augmented In-Context Example Selection aka KATE, kNN-Augmented In-Context Example Selection… A non-parametric in-context demonstration selection algorithm for pretrained language models that maps training instances and a test input i…	Curated	Algorithms	`AIMech:KATEkNNAugmentedInContextExampleSelection`	4 claims 3 sources
Katyusha Direct Negative-Momentum Acceleration for Stochastic Variance-Reduced Optimization aka Katyusha Momentum Accelerated Stochastic Variance Reduced Gradient, Katyusha Direct Primal-Only Accelerated Stochastic Gradient Method… Katyusha Direct Negative-Momentum Acceleration for Stochastic Variance-Reduced Optimization is a direct, primal-only accelerated stochastic…	Curated	Algorithms	`AIMech:KatyushaDirectNegativeMomentumAccelerationForStochasticVarianceReducedOptimization`	3 claims 3 sources
KD3A (Knowledge Distillation Based Decentralized Domain Adaptation) aka KD3A, Knowledge Distillation Based Decentralized Domain Adaptation… KD3A (Knowledge Distillation Based Decentralized Domain Adaptation) is an unsupervised multi-source decentralized domain adaptation algorith…	Curated	Algorithms	`AIMech:Kd3aKnowledgeDistillationBasedDecentralizedDomainAdaptation`	4 claims 3 sources
Kernel K-Means aka Kernelized K-Means A clustering algorithm that alternates nearest-feature-mean assignments and mean updates to minimize within-cluster squared distances in a k…	Curated	Algorithms	`AIMech:KernelKMeans`	4 claims 2 sources
Kernel Layer A layer that obtains the dot product of input values or subsets of input values.	AIO	Layer	`AIO:KernelLayer`	Imported
Kernel Principal Component Analysis aka Kernel PCA, KPCA A spectral feature-extraction algorithm that performs principal component analysis on centered implicit feature vectors by eigendecomposing…	Curated	Algorithms	`AIMech:KernelPCA`	4 claims 1 source
Kernel SHAP A model-agnostic Shapley-attribution estimator using weighted linear regression on feature-presence subsets.	Curated	Algorithms	`AIMech:KernelSHAP`	1 claim 1 source
Key-Value Memory Network aka KV-MemNN, Key-Value Memory Networks A neural memory architecture that answers a query by attending to keys and reading corresponding values from supplied key-value memory pairs…	Curated	Architectures	`AIMech:KeyValueMemoryNetwork`	6 claims 1 source
Kleinberg nonprincipal hub-authority extraction aka Nonprincipal eigenvector hub-authority extraction A link-analysis procedure that uses paired nonprincipal eigenvectors of the authority and hub Gram matrices of a query-focused directed page…	Curated	Algorithms	`AIMech:KleinbergNonprincipalHubAuthorityExtraction`	5 claims 1 source
Knowledge Transfer aka Inductive Transfer, Adaptation… A training strategy in which knowledge is passed from one entity such as a person organization or system to another facilitating learning an…	AIO	TrainingStrategy	`AIO:KnowledgeTransfer`	Imported
Knowledge-Grounded LLM aka Knowledge-Grounded Large Language Model, factual grounding… A large language model which incorporates external knowledge sources or knowledge bases into the model architecture, enabling it to generate…	AIO	Model	`AIO:KnowledgeGroundedLLM`	Imported
Knowledgeable Prompt-Tuning (KPT) Verbalizer aka Knowledgeable Prompt-Tuning, KPT… A prompt-tuning verbalizer construction, refinement, and aggregation method that expands each class anchor label v_0 into a multi-granularit…	Curated	Algorithms	`AIMech:KPTKnowledgeablePromptTuningVerbalizer`	4 claims 3 sources
Knuth backtrack-tree estimation aka Knuth tree-size estimator A randomized estimator of additive properties of a fixed backtracking tree that follows a sampled root-to-terminal path and weights each vis…	Curated	Algorithms	`AIMech:KnuthBacktrackTreeEstimation`	5 claims 2 sources
Kohonen Network aka KN, SOFM… A network that is an unsupervised technique producing a low-dimensional representation of high-dimensional data preserving topological struc…	AIO	Network	`AIO:KohonenNetwork`	Imported
KronA aka Kronecker Adapter, KronA Parameter-Efficient Kronecker Tuning… A parameter-efficient fine-tuning adapter that replaces low-rank bottleneck projections with a Kronecker product of two smaller factor matri…	Curated	Algorithms	`AIMech:KronA`	4 claims 3 sources
Krum and Multi-Krum Byzantine-Tolerant Gradient Descent aka Krum, Multi-Krum… A Euclidean-distance neighborhood gradient aggregation rule (Krum and Multi-Krum) for distributed stochastic gradient descent with n workers…	Curated	Algorithms	`AIMech:KrumAndMultiKrumByzantineTolerantGradientDescent`	4 claims 3 sources
KT-pFL (Parameterized Knowledge Transfer for Personalized Federated Learning) aka KT-pFL, Parameterized Knowledge Transfer for Personalized Federated Learning… A personalized group knowledge transfer federated learning algorithm (Zhang, Guo, Ma, Wang, Xu, & Wu 2021, Sections 3-4, Definitions 3.1-3.2…	Curated	Algorithms	`AIMech:KtPflParameterizedKnowledgeTransferForPersonalizedFederatedLearning`	4 claims 3 sources
L-Infinity Eigenvector Perturbation Bound and Robust Factor Covariance Estimation aka L-Infinity Eigenvector Perturbation Bound, Fan-Wang-Zhong L-Infinity Singular Vector Perturbation Theorem… A deterministic entrywise ($\ell_\infty$) eigenvector and singular-vector perturbation theory and heavy-tailed factor covariance estimation…	Curated	Mathematical Methods	`AIMech:LInfinityEigenvectorPerturbationBoundAndRobustFactorCovarianceEstimation`	3 claims 3 sources
L-SVRG and L-Katyusha (Loopless Variance-Reduced Gradient Methods) aka L-SVRG, Loopless SVRG… L-SVRG (Loopless Stochastic Variance-Reduced Gradient) and L-Katyusha (Loopless Katyusha) are single-loop stochastic variance-reduced optimi…	Curated	Algorithms	`AIMech:LSvrgAndLKatyushaLooplessVarianceReducedGradientMethods`	4 claims 3 sources
L1-Penalized and Post-Penalized Quantile Regression Process in High-Dimensional Sparse Models aka l1-Penalized Quantile Regression Process, Post-l1-Penalized Quantile Regression… L1-Penalized and Post-Penalized Quantile Regression Process in High-Dimensional Sparse Models is a family of distribution-free pivotal regul…	Curated	Algorithms	`AIMech:L1PenalizedAndPostPenalizedQuantileRegressionProcessInHighDimensionalSparseModels`	3 claims 3 sources
L2-loss support vector data description aka L2-loss SVDD, Squared-hinge-loss support vector data description A support-vector data-description algorithm that learns a feature-space sphere using squared-hinge penalties on squared-distance violations,…	Curated	Algorithms	`AIMech:L2LossSupportVectorDataDescription`	4 claims 1 source
L2GD (Loopless Local Gradient Descent for Mixture Federated Learning) aka L2GD, Loopless Local Gradient Descent… A personalized federated optimization formulation and randomized loopless algorithm (Hanzely & Richtarik 2020, Section 2, Equation 2; Sectio…	Curated	Algorithms	`AIMech:L2gdLooplessLocalGradientDescentForMixtureFederatedLearning`	4 claims 3 sources
Ladder Side-Tuning (LST) aka LST, Ladder Side-Tuning… A parameter- and memory-efficient transfer learning architecture that separates all trainable parameters from a frozen backbone network f in…	Curated	Architectures	`AIMech:LadderSideTuning`	4 claims 3 sources
Lagrange Coded Computing for Straggler-Resilient, Byzantine-Secure, and T-Private Distributed Polynomial Evaluation aka Lagrange Coded Computing, LCC… A universal algebraic coded distributed computing framework proposed by Yu, Li, Raviv, Mousavi Kalan, Soltanolkotabi, and Avestimehr (AISTAT…	Curated	Algorithms	`AIMech:LagrangeCodedComputingForResilientSecureAndPrivateDistributedLearning`	4 claims 3 sources
Lambda Layer A layer that wraps arbitrary expressions as a Layer object.	AIO	Layer	`AIO:LambdaLayer`	Imported
Language Interface LLM aka Interactive learning A large language model that supports interactive semantic parsing enabling users to provide feedback and corrections to dynamically refine a…	AIO	Model	`AIO:LanguageInterfaceLLM`	Imported
Language Model A model designed to predict the next word in a sequence or assign probabilities to sequences of words in natural language.	AIO	Model	`AIO:LanguageModel`	Imported
Laplacian Eigenmaps aka Laplacian Eigenmap A spectral embedding algorithm that builds a weighted neighborhood graph and uses nonconstant generalized eigenvectors of its graph Laplacia…	Curated	Algorithms	`AIMech:LaplacianEigenmaps`	3 claims 3 sources
LaPraDoR Iterative Contrastive Learning and Lexicon-Enhanced Dense Retrieval aka LaPraDoR, Large-scale Pretrained Dense Zero-shot Retriever… An unsupervised dual-tower dense retrieval pre-training and zero-shot inference algorithm that combines Inverse Cloze Task (ICT) and Dropout…	Curated	Algorithms	`AIMech:LaPraDoRUnsupervisedPretrainedDenseRetrieverZeroShot`	4 claims 3 sources
LaProp (Decoupled Momentum and Adaptivity Optimizer) aka LaProp Optimizer, LaProp Separating Momentum and Adaptivity in Adam… An adaptive first-order stochastic optimization algorithm that decouples parameter-space momentum from root-mean-square gradient adaptivity…	Curated	Algorithms	`AIMech:LaPropSeparatingMomentumAndAdaptivityInAdam`	5 claims 3 sources
Large Language Model aka LLM A language model consisting of a neural network with many parameters (typically billions of weights or more) trained on large quantities of…	AIO	Model	`AIO:LargeLanguageModel`	Imported
Large margin nearest neighbor aka LMNN, Large-margin nearest-neighbor classification… A supervised metric-learning method that fits a positive-semidefinite distance matrix by pulling fixed same-class target neighbors together…	Curated	Algorithms	`AIMech:LargeMarginNearestNeighbor`	2 claims 1 source
LargeVis A dimensionality-reduction and graph-visualization algorithm that constructs an approximate weighted nearest-neighbor graph and learns low-d…	Curated	Algorithms	`AIMech:LargeVis`	1 claim 1 source
Lasso Regression A regression analysis that performs both variable selection and regularization to enhance prediction accuracy and interpretability.	AIO	MachineLearningTask	`AIO:LassoRegression`	Imported
Late Dropout A neural-network training procedure that begins without dropout, activates it after a selected training cutoff and continues optimization wi…	Curated	Algorithms	`AIMech:LateDropout`	5 claims 2 sources
Latent Dirichlet allocation A hierarchical model for collections of discrete observations in which each document draws a Dirichlet-distributed mixture over a fixed fini…	Curated	Model Families	`AIMech:LatentDirichletAllocation`	1 claim 1 source
Layer A structure or network topology in a deep learning model that takes information from previous layers and passes it to the next layer.	AIO	Layer	`AIO:Layer`	Imported
Layer Layer A layer from which other layers can inherit.	AIO	Layer	`AIO:LayerLayer`	Imported
Layer-wise adaptive moments aka LAMB A gradient optimizer that combines coordinate-wise Adam moment scaling with layer-wise normalization of the resulting update direction, opti…	Curated	Algorithms	`AIMech:LayerWiseAdaptiveMoments`	7 claims 2 sources
Layer-wise adaptive rate control aka LARC A parameter-block learning-rate control rule whose clipping form limits a vanilla stochastic-gradient step by using the smaller of a global…	Curated	Algorithms	`AIMech:LayerWiseAdaptiveRateControl`	7 claims 2 sources
Layer-wise adaptive rate scaling A gradient optimization method that multiplies each selected layer or parameter block direction by a scalar based on its current weight L2 n…	Curated	Algorithms	`AIMech:LayerWiseAdaptiveRateScaling`	6 claims 1 source
Layer-wise relevance propagation aka LRP A prediction-decomposition framework that redistributes relevance backward through a classifier's computational layers toward its input feat…	Curated	Mathematical Methods	`AIMech:LayerWiseRelevancePropagation`	1 claim 1 source
LayerDrop: Structured Dropout for On-Demand Transformer Depth Reduction aka LayerDrop, LayerDrop Structured Layer Dropout for Transformers… A structured dropout regularization and on-demand depth-pruning algorithm for Transformer networks that constrains a binary Bernoulli mask M…	Curated	Algorithms	`AIMech:LayerDropStructuredDropoutForTransformerDepthReduction`	4 claims 3 sources
LayerNorm Layer aka LayerNorm A normalization layer that applies Layer Normalization over a mini-batch of inputs.	AIO	Layer	`AIO:LayerNormLayer`	Imported
LayerNormalization Layer A normalization layer that applies Layer Normalization over the inputs.	AIO	Layer	`AIO:LayerNormalizationLayer`	Imported
LazyBatchNorm1D Layer aka LazyBatchNorm1D A batch normalization layer that lazily initializes the num_features argument from the input size for 1D data.	AIO	Layer	`AIO:LazyBatchNorm1DLayer`	Imported
LazyBatchNorm2D Layer aka LazyBatchNorm2D A batch normalization layer that lazily initializes the num_features argument from the input size for 2D data.	AIO	Layer	`AIO:LazyBatchNorm2DLayer`	Imported
LazyBatchNorm3D Layer aka LazyBatchNorm3D A batch normalization layer that lazily initializes the num_features argument from the input size for 3D data.	AIO	Layer	`AIO:LazyBatchNorm3DLayer`	Imported
LazyInstanceNorm1D Layer aka LazyInstanceNorm1D A normalization layer that lazily initializes the num_features argument from the input size for 1D data.	AIO	Layer	`AIO:LazyInstanceNorm1DLayer`	Imported
LazyInstanceNorm2D Layer aka LazyInstanceNorm2D A normalization layer that lazily initializes the num_features argument from the input size for 2D data.	AIO	Layer	`AIO:LazyInstanceNorm2DLayer`	Imported
LazyInstanceNorm3D Layer aka LazyInstanceNorm3D A normalization that lazily initializes the num_features argument from the input size for 3D data.	AIO	Layer	`AIO:LazyInstanceNorm3DLayer`	Imported
LeakyReLU Layer An activation layer that applies the leaky rectified linear unit function element-wise.	AIO	Layer	`AIO:LeakyReLULayer`	Imported
Learned-Norm Pooling Unit aka Lp unit, Learned-norm pooling A parameterized neural unit that pools a group of learned linear projections by the power mean of their absolute deviations from learned cen…	Curated	Mathematical Methods	`AIMech:LearnedNormPoolingUnit`	4 claims 1 source
Learning Fair Representations aka LFR, Learned Fair Representations A prototype-based representation-learning algorithm that jointly balances reconstruction, supervised prediction and differences between grou…	Curated	Algorithms	`AIMech:LearningFairRepresentations`	2 claims 2 sources
Learning Hidden Unit Contributions aka LHUC A neural acoustic-model adaptation method that learns speaker- or environment-specific multipliers on hidden-unit activations while keeping…	Curated	Algorithms	`AIMech:LearningHiddenUnitContributions`	5 claims 1 source
Learning real-time A* aka LRTA*, Learning real-time A-star A real-time heuristic learning algorithm that moves to a minimum estimated path-cost neighbor, stores that minimum edge-cost-plus-heuristic…	Curated	Algorithms	`AIMech:LearningRealTimeAStar`	1 claim 2 sources
Least-angle regression aka LARS Regression that advances along directions equiangular to predictors most correlated with the residual.	Curated	Algorithms	`AIMech:LeastAngleRegression`	1 claim 1 source
Least-squares Analysis A regression analysis which approximates the solution of overdetermined systems by minimizing the sum of the squares of the residuals.	AIO	MachineLearningTask	`AIO:LeastsquaresAnalysis`	Imported
Leave-one-out mutual information upper bound aka Leave-one-out variational information upper bound An expectation-level upper bound on mutual information that compares a known conditional density for each paired sample with a mixture of co…	Curated	Mathematical Methods	`AIMech:LeaveOneOutMutualInformationUpperBound`	1 claim 1 source
Lee-Seung Multiplicative Updates aka Lee-Seung NMF Updates The Lee-Seung block multiplicative algorithms for nonnegative matrix factorization, using objective-specific elementwise factor rescaling to…	Curated	Algorithms	`AIMech:LeeSeungMultiplicativeUpdates`	3 claims 1 source
Left-truncated Cauchy combination test aka Truncated Cauchy Combination Test, Truncated Cauchy Test… A statistical p-value combination method that aggregates m dependent hypothesis test p-values p_1, ..., p_m in (0, 1] by bounding the left t…	Curated	Mathematical Methods	`AIMech:LeftTruncatedCauchyCombinationTest`	4 claims 2 sources
LG-FedAvg (Local Global Federated Averaging) aka LG-FedAvg, Local Global Federated Averaging… A personalized and communication-efficient federated learning algorithm (Liang, Liu, Ziyin, Allen, Auerbach, Brent, Salakhutdinov, & Morency…	Curated	Algorithms	`AIMech:LgFedAvgLocalGlobalRepresentationsFederatedLearning`	4 claims 3 sources
Lifelong Learning LLM aka Continual Learning LLM, Forever Learning… A large language model that continually acquires new knowledge over time without forgetting previously learned information maintaining a bal…	AIO	Model	`AIO:LifelongLearningLLM`	Imported
Lifted structured embedding loss aka Lifted structured loss A metric-learning objective that penalizes a positive pair’s Euclidean distance against negative distances incident to either endpoint, usin…	Curated	Mathematical Methods	`AIMech:LiftedStructuredEmbeddingLoss`	1 claim 2 sources
Lightweight and Dynamic Convolutions (LightConv and DynamicConv) aka LightConv and DynamicConv, Pay Less Attention with Lightweight and Dynamic Convolutions… Lightweight Convolution (LightConv) and Dynamic Convolution (DynamicConv) are linear-time O(n k d) sequence modeling primitives that replace…	Curated	Layers & Modules	`AIMech:PayLessAttentionWithLightweightAndDynamicConvolutions`	4 claims 3 sources
Limited discrepancy search aka LDS A backtracking tree-search strategy that repeatedly explores paths under an increasing upper limit on deviations from a successor-ordering h…	Curated	Algorithms	`AIMech:LimitedDiscrepancySearch`	3 claims 3 sources
Limited-memory BFGS aka L-BFGS, Limited-memory Broyden-Fletcher-Goldfarb-Shanno A limited-memory quasi-Newton optimization method using a bounded history of parameter and gradient differences to compute approximate inver…	Curated	Algorithms	`AIMech:LBFGS`	1 claim 1 source
Linear Coupling of Gradient and Mirror Descent for First-Order Optimization aka Allen-Zhu and Orecchia Linear Coupling Framework, Primal-Dual Linear Coupling Accelerated Gradient Method (AGM)… Linear Coupling of Gradient and Mirror Descent for First-Order Optimization is a primal-dual first-order algorithmic design and analysis fra…	Curated	Algorithms	`AIMech:LinearCouplingOfGradientAndMirrorDescentForFirstOrderOptimization`	3 claims 3 sources
Linear discriminant analysis aka LDA Gaussian discriminant classification sharing one covariance matrix across classes.	Curated	Model Families	`AIMech:LinearDiscriminantAnalysis`	1 claim 1 source
Linear Function A mathematical function that has the form f(x) = a + bx.	AIO	MathematicalFunction	`AIO:LinearFunction`	Imported
Linear Regression A regression analysis that is a linear approach for modeling the relationship between a scalar response and one or more explanatory variable…	AIO	MachineLearningTask	`AIO:LinearRegression`	Imported
Linear state-space layer aka LSSL A sequence-to-sequence layer defined by discretizing a linear continuous-time state-space system, with a state recurrence and, for zero init…	Curated	Layers & Modules	`AIMech:LinearStateSpaceLayer`	1 claim 1 source
Linking Bias A use and interpretation bias arising when network attributes obtained from user connections activities or interactions misrepresent true us…	AIO	Bias	`AIO:LinkingBias`	Imported
Lion (EvoLved Sign Momentum) aka Lion Optimizer, EvoLved Sign Momentum… A first-order stochastic optimization algorithm (EvoLved Sign Momentum) discovered via evolutionary symbolic program search with abstract ex…	Curated	Algorithms	`AIMech:LionEvolvedSignMomentumOptimization`	4 claims 3 sources
Lipschitz individual fairness aka Individual fairness (Dwork et al.), Fairness through awareness (Lipschitz criterion) An individual-fairness criterion requiring the distance between the output distributions assigned by a randomized classifier to any two indi…	Curated	Evaluation Criteria	`AIMech:LipschitzIndividualFairness`	1 claim 1 source
Liquid State Machine Network aka LSM A network that is a type of reservoir computer turning time-varying input into spatio-temporal activation patterns.	AIO	Network	`AIO:LiquidStateMachineNetwork`	Imported
LISA (Layerwise Importance Sampled AdamW) aka LISA, Layerwise Importance Sampled AdamW… A memory-efficient full-rank optimization algorithm for large language models that emulates the skewed layerwise update-norm distribution of…	Curated	Algorithms	`AIMech:LISALayerwiseImportanceSampledAdamW`	5 claims 3 sources
List-augmented recurrent neural network aka List RNN A recurrent sequence architecture whose neural controller accesses an external list through a movable read/write head, learning continuous m…	Curated	Architectures	`AIMech:ListAugmentedRecurrentNeuralNetwork`	6 claims 1 source
Lite Transformer with Long-Short Range Attention (LSRA) aka Lite Transformer, Long-Short Range Attention… Lite Transformer with Long-Short Range Attention (LSRA) is a computation- and memory-efficient Transformer architecture for resource-constra…	Curated	Architectures	`AIMech:LiteTransformerWithLongShortRangeAttention`	4 claims 3 sources
Liu modified discrete-state Gibbs sampler A discrete conditional sampling algorithm that proposes a category from the full conditional distribution with the current category excluded…	Curated	Algorithms	`AIMech:LiuModifiedGibbsSampler`	5 claims 1 source
Llama clustering aka Lattices by Leveraging Agglomerations and Multiple Ancestors An agglomerative clustering algorithm that unions each current cluster with a nearest neighboring cluster in successive rounds and retains t…	Curated	Algorithms	`AIMech:LlamaClustering`	7 claims 2 sources
LM Distill + Ranker Distill (Two-Round Knowledge Distillation for BERT Rankers) aka LM Distill + Ranker Distill, Two-Round LM and Ranker Knowledge Distillation for BERT Rerankers… A two-round knowledge distillation paradigm for compressing BERT-based neural rerankers (Gao, Dai, & Callan, ICTIR 2020) that explicitly dis…	Curated	Learning Paradigms	`AIMech:LMDistillPlusRankerDistillForBERTRankers`	4 claims 3 sources
LM-BFF Better Few-Shot Fine-Tuning of Language Models aka LM-BFF, Better Few-Shot Fine-Tuning of Language Models… A few-shot fine-tuning framework for moderately sized pretrained masked language models that reformulates classification and bounded-interva…	Curated	Algorithms	`AIMech:LMBFFBetterFewShotFineTuning`	4 claims 3 sources
Local interpretable model-agnostic explanations aka LIME A prediction-explanation method fitting an interpretable surrogate to locally weighted samples of a model's behavior.	Curated	Algorithms	`AIMech:LIME`	1 claim 1 source
Local outlier factor aka LOF An unsupervised local outlier-scoring procedure that compares each observation's inverse mean reachability distance with those of its tie-in…	Curated	Algorithms	`AIMech:LocalOutlierFactor`	8 claims 3 sources
Local search space learning real-time A* aka LSS-LRTA, Local search space LRTA A real-time heuristic learning algorithm that constructs a bounded local search space with A*, repairs the heuristic values of its expanded…	Curated	Algorithms	`AIMech:LocalSearchSpaceLearningRealTimeAStar`	6 claims 2 sources
Local SGD Periodic Model Averaging Parallel Stochastic Gradient Descent aka Local SGD, Parallel Restarted SGD… A communication-efficient parallel stochastic optimization algorithm (Local SGD) in which K workers independently advance local parameter ve…	Curated	Algorithms	`AIMech:LocalSgdPeriodicAveragingParallelStochasticGradientDescent`	4 claims 3 sources
Locally Linear Embedding aka LLE A nonlinear dimensionality-reduction algorithm that learns sparse, sum-to-one linear reconstructions of each point from nearby points and co…	Curated	Algorithms	`AIMech:LocallyLinearEmbedding`	2 claims 2 sources
Locally-connected Layer A layer that works similarly to the Convolution1D layer, except that weights are unshared, that is, a different set of filters is applied at…	AIO	Layer	`AIO:LocallyconnectedLayer`	Imported
LocallyConnected1D Layer A locally-connected layer for 1D inputs where each patch of the input is convolved with a different set of filters.	AIO	Layer	`AIO:LocallyConnected1DLayer`	Imported
LocallyConnected2D Layer A locally-connected layer for 2D inputs where each patch of the input is convolved with a different set of filters.	AIO	Layer	`AIO:LocallyConnected2DLayer`	Imported
LocalResponseNorm Layer aka LocalResponseNorm A normalization layer that applies local response normalization over an input signal composed of several input planes.	AIO	Layer	`AIO:LocalResponseNormLayer`	Imported
LocoProp Layerwise Local Loss Backpropagation Optimization aka LocoProp, LocoProp-S… LocoProp (Local Loss Optimization) is a layerwise neural network optimization framework that enhances each standard backpropagation pass by…	Curated	Algorithms	`AIMech:LocoPropLayerwiseLocalLossBackpropagationOptimization`	4 claims 3 sources
Log-bilinear language model aka LBL A next-word language architecture that linearly combines position-specific transforms of context-word embeddings and normalizes their biline…	Curated	Architectures	`AIMech:LogBilinearLanguageModel`	1 claim 2 sources
Logarithmic opinion pool aka Log opinion pool, Logarithmic pooling A probability-aggregation method that forms a normalized weighted geometric mean of expert distributions over the same outcomes, using nonne…	Curated	Mathematical Methods	`AIMech:LogarithmicOpinionPool`	1 claim 2 sources
Logistic Regression A regression analysis that estimates the probability of an event occurring by modeling the log-odds of the event as a linear combination of…	AIO	MachineLearningTask	`AIO:LogisticRegression`	Imported
Long Short Term Memory aka LSTM A recurrent neural network with feedback connections that processes entire sequences of data.	AIO	Network	`AIO:LongShortTermMemory`	Imported
LongLoRA and Shifted Sparse Attention (S^2-Attn) aka LongLoRA, Shifted Sparse Attention… LongLoRA is an efficient long-context fine-tuning framework for pretrained large language models that combines two core components: (1) Shif…	Curated	Algorithms	`AIMech:LongloraAndShiftedSparseAttention`	4 claims 3 sources
Lookahead Optimizer aka Lookahead k Steps Forward 1 Step Back Optimization, Fast-and-Slow Weights Linear Interpolation Optimizer… An orthogonal outer-loop optimization wrapper algorithm that maintains two sets of parameters—slow weights phi and fast weights theta—by syn…	Curated	Algorithms	`AIMech:LookaheadOptimizer`	4 claims 3 sources
Lookup Conditional Distribution Prediction aka Lookup CDP A computational variant of conditional distribution prediction that precomputes or memoizes fixed-model subtree expansion-count estimates fo…	Curated	Algorithms	`AIMech:LookupConditionalDistributionPrediction`	5 claims 1 source
LoRA+ (Asymmetric Learning Rate Low-Rank Adaptation) aka LoRA+, LoRA Plus… LoRA+ is an optimization algorithm for Low-Rank Adaptation (LoRA) of large-width neural networks that sets distinct, asymmetrically scaled l…	Curated	Algorithms	`AIMech:LoraPlusEfficientLowRankAdaptationWithAsymmetricLearningRates`	4 claims 3 sources
LoRA-drop aka LoRA-Drop Output-Evaluated Parameter Pruning, Output-Based LoRA Layer Pruning and Sharing… A parameter-efficient fine-tuning algorithm that evaluates the layer-wise importance of low-rank adapters using the normalized sum of square…	Curated	Algorithms	`AIMech:LoRADrop`	4 claims 3 sources
LoRA-FA aka LoRA with Frozen-A, Memory-Efficient Low-Rank Adaptation with Frozen Projection-Down Matrix… A memory-efficient low-rank adaptation algorithm that freezes the randomly initialized down-projection matrix A and updates only the zero-in…	Curated	Algorithms	`AIMech:LoRAFA`	4 claims 3 sources
LoRA-Fine-Tuning-Aware Quantization (LoftQ) aka LoftQ, LoRA-Fine-Tuning-Aware Quantization… LoRA-Fine-Tuning-Aware Quantization (LoftQ) is a joint quantization and low-rank adapter initialization framework for quantized parameter-ef…	Curated	Algorithms	`AIMech:LoftqLoraFineTuningAwareQuantization`	3 claims 3 sources
LoRA-Flow aka LoRA-Flow Dynamic LoRA Fusion, Token- and Layer-Level Dynamic LoRA Fusion (LoRA-Flow)… A dynamic multi-LoRA fusion algorithm for autoregressive language generation that computes token-step and layer-specific fusion weights w^l_…	Curated	Algorithms	`AIMech:LoRAFlow`	4 claims 3 sources
LoRA-GA aka Low-Rank Adaptation with Gradient Approximation, Low-Rank Gradient Approximation LoRA Initialization… A low-rank adaptation initialization algorithm that aligns the initial update direction of a low-rank adapter product eta B A with the first…	Curated	Algorithms	`AIMech:LoRAGA`	4 claims 3 sources
LoRA-XS aka Low-Rank Adaptation with Extremely Small Number of Parameters, Frozen-SVD Latent r-by-r Low-Rank Adaptation… An ultra-parameter-efficient low-rank adaptation algorithm that initializes and freezes each module's low-rank projection matrices from the…	Curated	Algorithms	`AIMech:LoRAXS`	4 claims 3 sources
LoraHub aka LoraHub Dynamic LoRA Composition, LoraHub Gradient-Free Cross-Task LoRA Assembly… A few-shot cross-task generalization framework that dynamically assembles N upstream task-specific LoRA modules {(A_i, B_i)}_{i=1}^N into a…	Curated	Algorithms	`AIMech:LoraHub`	4 claims 3 sources
LoRAMoE aka LoRAMoE Plugin with Localized Balancing Constraint, Localized-Balanced Mixture of LoRA Experts for World Knowledge Retention… A Mixture-of-Experts-style parameter-efficient fine-tuning architecture that freezes the pre-trained backbone feed-forward linear weights W_…	Curated	Architectures	`AIMech:LoRAMoE`	4 claims 3 sources
Loss Of Situational Awareness Bias An individual bias occurring when automation leads to humans being unaware of their situation making them unprepared to assume control in co…	AIO	Bias	`AIO:LossOfSituationalAwarenessBias`	Imported
Loss-Specific Optimal Eigenvalue Shrinkage for Spiked Covariance Matrices aka Donoho-Gavish-Johnstone Spiked Covariance Optimal Eigenvalue Shrinkage, Loss-Specific Nonlinear Eigenvalue Shrinkage in the Spiked Covariance Model… A high-dimensional covariance estimation methodology introduced by Donoho, Gavish, and Johnstone (2018, The Annals of Statistics 46(4):1742-…	Curated	Mathematical Methods	`AIMech:LossSpecificOptimalEigenvalueShrinkageForSpikedCovarianceMatrices`	3 claims 3 sources
Loss-Specific Optimal Singular Value Shrinkage for Low-Rank Matrix Denoising aka Optimal Shrinkage of Singular Values, Gavish-Donoho Optimal Singular Value Shrinker… Loss-specific optimal singular value shrinkage is a high-dimensional matrix denoising methodology for recovering a fixed-rank signal matrix…	Curated	Mathematical Methods	`AIMech:LossSpecificOptimalSingularValueShrinkageForMatrixDenoising`	3 claims 3 sources
Lottery Ticket Sparse Fine-Tuning aka LT-SFT, Composable Lottery-Ticket Sparse Fine-Tuning… A modular two-phase sparse fine-tuning algorithm for pretrained language models inspired by the Lottery Ticket Hypothesis that first perform…	Curated	Algorithms	`AIMech:LTSFTLotteryTicketSparseFineTuning`	4 claims 3 sources
Low-rank adaptation aka LoRA A parameter-efficient adaptation method that freezes pretrained weights and learns additive low-rank matrix updates.	Curated	Algorithms	`AIMech:LoRA`	2 claims 1 source
Low-Resource LLM aka Low-Resource Language Model, low-resource languages… A large language model which is optimized for performance in scenarios with limited data, computational resources, or for languages with spa…	AIO	Model	`AIO:LowResourceLLM`	Imported
Lower Power Genetic Algorithm A processor-configuration optimizer that evolves a symmetry-based network encoding through constrained swap mutation and rank-grouped offspr…	Curated	Algorithms	`AIMech:LowerPowerGeneticAlgorithm`	5 claims 1 source
LPPool1D Layer aka LPPool1D A pooling layer that applies 1D power-average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:LPPool1DLayer`	Imported
LPPool2D Layer aka LPPool2D A pooling layer that applies 2D power-average pooling over an input signal composed of several input planes.	AIO	Layer	`AIO:LPPool2DLayer`	Imported
LSTM Layer A recurrent layer that implements the Long Short-Term Memory architecture.	AIO	Layer	`AIO:LSTMLayer`	Imported
LSTMCell Layer A layer that processes one step within the whole time sequence input for an LSTM layer.	AIO	Layer	`AIO:LSTMCellLayer`	Imported
MA* A memory-controlled heuristic tree-search algorithm that stores separate lower bounds for absent and all successors, expands promising conti…	Curated	Algorithms	`AIMech:MAStar`	6 claims 1 source
MABLE Maximum Approximate Bernstein Likelihood Estimation in Proportional Hazards Model for Interval-Censored Data aka MABLE Proportional Hazards Estimator, Maximum Approximate Bernstein Likelihood Estimator for Interval-Censored Data… A semiparametric survival regression method for Cox's proportional hazards model under interval-censored data that parameterizes the baselin…	Curated	Mathematical Methods	`AIMech:MABLEMaximumApproximateBernsteinLikelihoodProportionalHazardsIntervalCensoring`	4 claims 3 sources
Machine Learning Task aka Machine Learning A process intended to build methods that learn from data.	AIO	MachineLearningTask	`AIO:MachineLearningTask`	Imported
MAD-X Multiple Adapters for Cross-Lingual Transfer aka MAD-X, Multiple Adapters for Cross-Lingual Transfer… A modular adapter-based architecture and transfer framework for pre-trained multilingual Transformers that combines three distinct adapter m…	Curated	Architectures	`AIMech:MADXMultipleAdaptersForCrossLingualTransfer`	4 claims 3 sources
Madam aka Multiplicative Adaptive Moments Optimizer, B-Bit Logarithmic Number System Madam Optimizer… A multiplicative adaptive moments optimization algorithm for compositional neural networks that maintains an exponential moving average of s…	Curated	Algorithms	`AIMech:Madam`	4 claims 3 sources
MADGRAD (Momentumized, Adaptive, Dual Averaged Gradient Method) aka MADGRAD Optimizer, Momentumized Adaptive Dual Averaged Gradient… An AdaGrad-family stochastic optimization algorithm (Algorithm 1) built on Nesterov dual averaging with double averaging that centers the qu…	Curated	Algorithms	`AIMech:MADGRADMomentumizedAdaptiveDualAveragedGradientOptimization`	4 claims 3 sources
Mamba sequence architecture aka Mamba A neural sequence architecture built from repeated blocks containing input-dependent selective state-space transformations.	Curated	Architectures	`AIMech:Mamba`	1 claim 1 source
Manifold Learning A dimensionality reduction method based on the assumption that observed data lie on a low-dimensional manifold embedded in a higher-dimensio…	AIO	MachineLearningTask	`AIO:ManifoldLearning`	Imported
Manifold Mixup A neural-network training procedure that interpolates paired examples’ representations at a selected network layer and interpolates their la…	Curated	Algorithms	`AIMech:ManifoldMixup`	1 claim 1 source
MAO* A memory-controlled heuristic search algorithm for acyclic AND/OR graphs that expands a marked partial solution graph, revises lower-bound c…	Curated	Algorithms	`AIMech:MAOStar`	6 claims 1 source
Marcenko-Pastur Convex Optimization Spectrum Estimation for Large Covariance Matrices aka El Karoui Marcenko-Pastur Stieltjes-Transform Convex Spectrum Estimator, Random Matrix Theory Linear-Programming Population Spectral Distribution Estimator… Marcenko-Pastur Convex Optimization Spectrum Estimation for Large Covariance Matrices is a nonparametric high-dimensional spectral distribut…	Curated	Mathematical Methods	`AIMech:MarcenkoPasturConvexOptimizationSpectrumEstimation`	3 claims 3 sources
Margin-MSE Cross-Architecture Knowledge Distillation for Neural Ranking aka Margin-MSE, Margin-MSE Cross-Architecture Knowledge Distillation… A cross-architecture knowledge distillation method for neural information retrieval (Hofstätter, Althammer, Schröder, Sertkan, & Hanbury, 20…	Curated	Learning Paradigms	`AIMech:MarginMSECrossArchitectureKnowledgeDistillationForNeuralRanking`	4 claims 3 sources
MARINA Faster Non-Convex Distributed Learning with Compression aka MARINA, VR-MARINA… A communication-efficient nonconvex distributed optimization method (MARINA, together with its variance-reduced finite-sum/online variant VR…	Curated	Algorithms	`AIMech:MarinaFasterNonconvexDistributedLearningWithCompression`	4 claims 3 sources
Markov Chain aka MC, MP… A network that is a stochastic model describing a sequence of possible events where the probability of each event depends only on the previo…	AIO	Network	`AIO:MarkovChain`	Imported
Markov Chain Monte Carlo Stochastic Approximation Expectation Maximization aka MCMC-SAEM, SAEM-MCMC… A stochastic approximation EM extension that advances a persistent latent-state Markov chain targeting the conditional distribution at the c…	Curated	Algorithms	`AIMech:MarkovChainMonteCarloStochasticApproximationExpectationMaximization`	4 claims 2 sources
Markov decision process aka MDP A sequential decision model with states, actions, Markov transitions, and rewards.	Curated	Model Families	`AIMech:MarkovDecisionProcess`	1 claim 1 source
Markov random field aka MRF, Markov network An undirected graphical probability model associating potential functions with variable groups.	Curated	Model Families	`AIMech:MarkovRandomField`	1 claim 1 source
MARS (Make vAriance Reduction Shine Preconditioned Optimizer Framework) aka MARS Optimizer Framework, MARS-AdamW and MARS-Lion and MARS-Shampoo… A unified variance-reduced preconditioned stochastic optimization framework for training large deep models that combines an Online Mirror De…	Curated	Algorithms	`AIMech:MarsVarianceReducedPreconditionedGradientOptimization`	5 claims 3 sources
Masked Language Model aka bidirectional encoder, denoising autoencoder A language model that is trained to predict randomly masked tokens in a sequence based on the remaining unmasked tokens allowing it to build…	AIO	Model	`AIO:MaskedLanguageModel`	Imported
Masking Layer A layer that masks a sequence by using a mask value to skip timesteps.	AIO	Layer	`AIO:MaskingLayer`	Imported
MATCHA Matching Decomposition Sampling for Decentralized SGD aka MATCHA, Matching Decomposition Sampling for Decentralized SGD… A topology-aware decentralized stochastic gradient descent algorithm (MATCHA) that decomposes a base communication graph G(V, E) into M vert…	Curated	Algorithms	`AIMech:MatchaMatchingDecompositionSamplingForDecentralizedSgd`	4 claims 3 sources
Matched Input-Output Layer An input layer with a shape corresponding to that of the output layer.	AIO	Layer	`AIO:MatchedInputOutputLayer`	Imported
Matching pursuit A greedy fixed-dictionary approximation algorithm that repeatedly selects a unit-norm atom by its absolute correlation with the current resi…	Curated	Algorithms	`AIMech:MatchingPursuit`	5 claims 2 sources
MatDot and PolyDot Codes for Straggler-Resilient Coded Matrix Multiplication aka MatDot Codes, PolyDot Codes… A family of algebraic coded matrix-multiplication schemes proposed by Dutta, Fahim, Haddadpour, Jeong, Cadambe, and Grover (2017/2020) that…	Curated	Algorithms	`AIMech:MatDotAndPolyDotCodesForStragglerResilientCodedMatrixMultiplication`	4 claims 3 sources
Mathematical Function A mathematical rule that gives the value of a dependent variable corresponding to specified values of one or more independent variables.	AIO	MathematicalFunction	`AIO:MathematicalFunction`	Imported
Max-LET CoPE scheduling An execution-focused CoPE scheduling schema that fixes each candidate action head to latest start times under a selected induced deadline, d…	Curated	Algorithms	`AIMech:MaxLETCoPE`	4 claims 1 source
Max-value Entropy Search A Bayesian global optimization algorithm that chooses evaluations using an approximate information acquisition for the latent maximum functi…	Curated	Algorithms	`AIMech:MaxValueEntropySearch`	6 claims 2 sources
MAXCFU aka Optimization-based counterfactual-fairness sensitivity A multivariate sensitivity algorithm that uses gradient ascent through fitted additive-noise models to search for large counterfactual predi…	Curated	Evaluation Methods	`AIMech:MaxCFU`	2 claims 2 sources
Maximum candidates per node in sequence beam pruning A sequence-beam pruning procedure that limits how many retained candidate extensions may come from the same predecessor hypothesis, discardi…	Curated	Algorithms	`AIMech:PerNodeCandidateBeamPruning`	2 claims 2 sources
Maximum coding likelihood estimation aka Coding likelihood estimation, Coding maximum likelihood estimation A conditional parameter-estimation method that selects mutually non-neighboring sites in a Markov field and maximizes their joint conditiona…	Curated	Algorithms	`AIMech:MaximumCodingLikelihoodEstimation`	1 claim 2 sources
Maximum Layer A merging layer that computes the maximum (element-wise) of a list of inputs.	AIO	Layer	`AIO:MaximumLayer`	Imported
Maximum pseudolikelihood estimation aka MPLE A parameter-estimation method that maximizes the product of a specified model’s sitewise full conditional probabilities or densities evaluat…	Curated	Algorithms	`AIMech:MaximumPseudolikelihoodEstimation`	1 claim 1 source
Maxout Unit aka Maxout A parameterized neural unit that outputs the maximum of a finite group of learned affine functions of its input.	Curated	Mathematical Methods	`AIMech:MaxoutUnit`	5 claims 2 sources
MaxPooling1D Layer aka MaxPool1D, MaxPooling1D A pooling layer that performs max pooling operation for temporal data.	AIO	Layer	`AIO:MaxPooling1DLayer`	Imported
MaxPooling2D Layer aka MaxPool2D, MaxPooling2D A pooling layer that performs max pooling operation for spatial data.	AIO	Layer	`AIO:MaxPooling2DLayer`	Imported
MaxPooling3D Layer aka MaxPool3D, MaxPooling3D A pooling layer that performs max pooling operation for 3D data (spatial or spatio-temporal).	AIO	Layer	`AIO:MaxPooling3DLayer`	Imported
MaxUnpool1D Layer aka MaxUnpool1D A pooling layer that computes a partial inverse of MaxPool1D.	AIO	Layer	`AIO:MaxUnpool1DLayer`	Imported
MaxUnpool2D Layer aka MaxUnpool2D A pooling layer that computes a partial inverse of MaxPool2D.	AIO	Layer	`AIO:MaxUnpool2DLayer`	Imported
MaxUnpool3D Layer aka MaxUnpool3D A pooling layer that computes a partial inverse of MaxPool3D.	AIO	Layer	`AIO:MaxUnpool3DLayer`	Imported
MAX–MIN Ant System aka MMAS An ant-colony optimization algorithm that reinforces solution components from a single selected best ant per iteration, constrains pheromone…	Curated	Algorithms	`AIMech:MaxMinAntSystem`	1 claim 1 source
ME-BERT Multi-Vector Dense Retrieval aka ME-BERT, Multi-Vector BERT Dense Retrieval… A multi-vector dense retrieval architecture and capacity-bounded representation framework that represents each query as a single projected […	Curated	Architectures	`AIMech:MEBERTMultiVectorDenseRetrieval`	4 claims 3 sources
Mean shift Mode-seeking clustering that moves candidate centers toward local density maxima.	Curated	Algorithms	`AIMech:MeanShift`	1 claim 1 source
Mean Teacher A semi-supervised classifier-training procedure that regularizes a student prediction toward the prediction of a same-architecture teacher w…	Curated	Algorithms	`AIMech:MeanTeacher`	1 claim 2 sources
Mean-field Boltzmann learning aka Mean-field theory learning algorithm A deterministic approximation to Boltzmann-machine parameter learning that substitutes mean-field phase statistics for stochastic equilibriu…	Curated	Algorithms	`AIMech:MeanFieldBoltzmannLearning`	1 claim 1 source
Measure-theoretic step-up false discovery rate control over a continuum of null hypotheses aka Blanchard-Delattre-Roquain Continuum Step-Up FDR Control, Weakly PRDS Continuum Multiple Testing Framework… A measure-theoretic multiple hypothesis testing framework developed by Gilles Blanchard, Sylvain Delattre, and Etienne Roquain (2014, Bernou…	Curated	Mathematical Methods	`AIMech:ContinuumMeasureSpaceStepUpFDRControl`	4 claims 3 sources
Measured Continuous Greedy Algorithm for Constrained Monotone and Non-Monotone Submodular Maximization aka Measured Continuous Greedy, Unified Continuous Greedy Algorithm… Measured Continuous Greedy is a unified continuous relaxation algorithm for maximizing the multilinear extension F(y) = E[f(R(y))] of a non-…	Curated	Algorithms	`AIMech:MeasuredContinuousGreedySubmodularMaximization`	3 claims 3 sources
Measurement Bias A selection and sampling bias arising when features and labels are proxies for desired quantities potentially leading to differential perfor…	AIO	Bias	`AIO:MeasurementBias`	Imported
MELoRA aka Mini-Ensemble Low-Rank Adapters, Block-Diagonal Mini-Ensemble LoRA… A parameter-efficient fine-tuning algorithm that partitions the input and output feature dimensions of a frozen linear layer into n disjoint…	Curated	Algorithms	`AIMech:MELoRA`	4 claims 3 sources
Memory Cell Layer A layer of cells, each with an internal state or weights.	AIO	Layer	`AIO:MemoryCellLayer`	Imported
Memory Network aka Memory Networks A family of learning models that combines an addressable memory with input conversion, memory updating, output inference and response compon…	Curated	Model Families	`AIMech:MemoryNetwork`	6 claims 1 source
Memory-Augmented LLM aka Memory-Augmented Large Language Model, external memory A large language model which incorporates external writable and readable memory components, allowing it to store and retrieve information ov…	AIO	Model	`AIO:MemoryAugmentedLLM`	Imported
Memory-reduced best-first beam search for sequence decoding A capacity-limited variant of per-length best-first sequence beam search that, when its chosen total queue capacity is reached, removes the…	Curated	Algorithms	`AIMech:MemoryReducedSequenceBeamSearch`	2 claims 2 sources
Merging Layer A layer used to merge a list of inputs.	AIO	Layer	`AIO:MergingLayer`	Imported
Meta-Learning A machine learning task that automatically learns from metadata about machine learning experiments.	AIO	MachineLearningTask	`AIO:MetaLearning`	Imported
Meta-Learning LLM aka Meta-Learning Large Language Model, few-shot adaptation… A large language model which is trained in a way that allows it to quickly adapt to new tasks or datasets through only a few examples or fin…	AIO	Model	`AIO:MetaLearningLLM`	Imported
Metric Learning aka Distance Metric Learning A deep neural network that learns a representation function mapping objects into an embedded space.	AIO	Network	`AIO:MetricLearning`	Imported
Metropolis-adjusted Langevin algorithm aka MALA A Metropolis–Hastings sampler that proposes a Gaussian step with drift proportional to the target log-density gradient and corrects the asym…	Curated	Algorithms	`AIMech:MetropolisAdjustedLangevinAlgorithm`	2 claims 2 sources
Metropolis-within-Gibbs sampling aka MWG A componentwise Monte Carlo scheme that uses Metropolis–Hastings transitions targeting full conditional distributions for one or more coordi…	Curated	Algorithms	`AIMech:MetropolisWithinGibbs`	1 claim 1 source
Metropolis–Hastings sampling aka MH A Markov chain Monte Carlo algorithm that proposes a new state from a specified transition distribution and accepts it with the smaller of o…	Curated	Algorithms	`AIMech:MetropolisHastings`	2 claims 2 sources
MEX Operator aka MEX (SimNets) A scalar aggregation operator that returns log(mean(exp(xi times input)))/xi for a nonzero real parameter xi, with its continuous zero-param…	Curated	Mathematical Methods	`AIMech:MEXOperator`	4 claims 1 source
MicroAdam (Sparse-Gradient Adaptive Optimization with Quantized Error Feedback) aka MicroAdam, MicroAdam Optimizer… A memory-efficient adaptive optimization algorithm that replaces dense first- and second-moment optimizer states with a circular sliding win…	Curated	Algorithms	`AIMech:MicroAdamSparseGradientWithQuantizedErrorFeedbackOptimization`	5 claims 3 sources
MiLoRA aka Minor Singular Component Based Low-Rank Adaptation, Minor Singular Component LoRA… A parameter-efficient low-rank adaptation algorithm that decomposes each pre-trained weight matrix via SVD into a frozen principal matrix W_…	Curated	Algorithms	`AIMech:MiLoRA`	4 claims 3 sources
Mime Framework for Mimicking Centralized Stochastic Algorithms in Federated Learning aka Mime, MimeLite… A general federated optimization framework (Mime and MimeLite) that adapts arbitrary centralized stateful stochastic optimizers A = (U, V) (…	Curated	Algorithms	`AIMech:MimeMimickingCentralizedStochasticAlgorithmsInFederatedLearning`	4 claims 3 sources
Min-conflicts heuristic aka Min-conflicts A constraint-repair value-selection heuristic that uses a complete assignment to choose a value for a conflicted variable with as few confli…	Curated	Algorithms	`AIMech:MinConflicts`	1 claim 1 source
MiniLM (Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers) aka MiniLM, Deep Self-Attention Distillation… A task-agnostic knowledge distillation framework for compressing pre-trained Transformer language models (Wang, Wei, Dong, Bao, Yang, & Zhou…	Curated	Learning Paradigms	`AIMech:MiniLMDeepSelfAttentionDistillationForTaskAgnosticCompression`	4 claims 3 sources
Minimax Estimation Rates for High-Dimensional Linear Regression Over l_q-Balls aka Minimax Rates of Estimation for High-Dimensional Linear Regression Over l_q-Balls (Raskutti, Wainwright, & Yu 2011), Information-Theoretic Minimax l_p-Parameter and l_2-Prediction Risk Over l_q-Balls… Minimax Estimation Rates for High-Dimensional Linear Regression Over l_q-Balls is an information-theoretic and empirical-process statistical…	Curated	Mathematical Methods	`AIMech:MinimaxEstimationRatesForHighDimensionalLinearRegressionOverLqBalls`	3 claims 3 sources
Minimax Risk and Least-Favorable Subspace Characterization of Matrix Denoising by Singular Value Soft Thresholding aka Minimax Risk of Singular Value Soft Thresholding (SVST), Donoho-Gavish Proportional-Rank SVST Minimax AMSE M(rho, beta)… A high-dimensional statistical decision-theoretic methodology introduced by Donoho and Gavish (2014, The Annals of Statistics 42(6):2413-244…	Curated	Mathematical Methods	`AIMech:MinimaxRiskOfMatrixDenoisingBySingularValueSoftThresholding`	3 claims 3 sources
Minimax-Optimal Inference and Rank-Breaking from Plackett-Luce Partial Rankings aka Plackett-Luce Partial Ranking MLE and Full Rank-Breaking, Hajek-Oh-Xu Minimax-Optimal Inference from Partial Rankings… A statistical estimation and rank-aggregation methodology (introduced by Bruce Hajek, Sewoong Oh, and Jiaming Xu in 2014) for inferring late…	Curated	Mathematical Methods	`AIMech:MinimaxOptimalInferenceAndRankBreakingFromPlackettLucePartialRankings`	3 claims 3 sources
Minimax-Optimal Sparse Additive Models Over Kernel Classes via Convex Programming aka Minimax-Optimal Rates for Sparse Additive Models Over Kernel Classes via Convex Programming (Raskutti, Wainwright, & Yu 2012), Doubly-Penalized (L2(Q_n), 1) and (H, 1) Second-Order Cone Program Sparse Additive Kernel Estimator… Minimax-Optimal Sparse Additive Models Over Kernel Classes via Convex Programming is a non-parametric high-dimensional estimation and minima…	Curated	Mathematical Methods	`AIMech:MinimaxOptimalSparseAdditiveModelsOverKernelClassesViaConvexProgramming`	3 claims 3 sources
Minimax-Optimal Tapering for High-Dimensional Covariance Matrix Estimation aka Trapezoidal Tapering Covariance Estimator, Cai-Zhang-Zhou Tapering Estimator… Minimax-optimal tapering for high-dimensional covariance matrix estimation is a linear location-equivariant covariance regularization method…	Curated	Mathematical Methods	`AIMech:MinimaxOptimalTaperingForHighDimensionalCovarianceMatrixEstimation`	3 claims 3 sources
Minimin search with alpha pruning A bounded single-agent lookahead planner that backs up minimum path-cost-plus-heuristic frontier estimates and prunes branches using an incu…	Curated	Algorithms	`AIMech:MiniminAlphaPruning`	5 claims 2 sources
Minimum Layer A merging layer that computes the minimum (element-wise) of a list of inputs.	AIO	Layer	`AIO:MinimumLayer`	Imported
Mixed memory Markov model A family of compact temporal probability models whose component transition distributions are convex mixtures of transition tables indexed by…	Curated	Model Families	`AIMech:MixedMemoryMarkovModel`	1 claim 1 source
Mixed-membership model for scientific publications A generative document model in which one Dirichlet-distributed membership vector mixes aspect-specific word distributions for an abstract an…	Curated	Model Families	`AIMech:MixedMembershipModelForScientificPublications`	2 claims 1 source
MixMatch A semi-supervised classifier-training procedure that averages predictions over augmented unlabeled inputs, sharpens the resulting soft targe…	Curated	Algorithms	`AIMech:MixMatch`	1 claim 1 source
Mixture density network aka MDN A neural conditional-density architecture whose input-dependent outputs parameterize the mixing weights and component distributions of a fin…	Curated	Architectures	`AIMech:MixtureDensityNetwork`	1 claim 1 source
Mixture-approximation node-splitting conflict diagnostic aka Gaussian-mixture node-splitting conflict check, Mixture-approximated separator conflict diagnostic A Bayesian directed acyclic graph (DAG) node-splitting conflict diagnostic algorithm that partitions observed data around a selected separat…	Curated	Algorithms	`AIMech:MixtureApproximationNodeSplittingDiagnostic`	4 claims 2 sources
Mixture-of-Experts LLM aka Mixture-of-Experts Large Language Model, MoE Large Language Model… A large language model which dynamically selects and combines outputs from multiple expert submodels, allowing for efficient scaling by cond…	AIO	Model	`AIO:MixtureofExpertsLLM`	Imported
Mixtures of Probabilistic Principal Component Analyzers aka Mixtures of Probabilistic PCA, MPPCA… A finite Gaussian mixture whose components each have a linear standard-normal latent factor and component-specific isotropic observation noi…	Curated	Model Families	`AIMech:MixturesOfProbabilisticPCA`	5 claims 1 source
MixUp A training-data interpolation procedure that fits a predictor to convex combinations of example inputs and their corresponding targets using…	Curated	Algorithms	`AIMech:MixUp`	1 claim 1 source
MobileBERT: Compact Task-Agnostic BERT with Bottleneck Structures and Progressive Knowledge Transfer aka MobileBERT, MobileBERT Bottleneck Transformer Architecture… A deep-and-thin task-agnostic 24-layer Transformer architecture and progressive distillation framework that compresses BERT width rather tha…	Curated	Architectures	`AIMech:MobileBERTCompactTaskAgnosticBERTWithBottlenecks`	4 claims 3 sources
MOCHA (Systems-Aware Primal-Dual Federated Multi-Task Learning) aka MOCHA, Mocha Federated Multi-Task Learning… A systems-aware bi-convex primal-dual optimization framework for federated multi-task learning (Smith, Chiang, Sanjabi, & Talwalkar 2017, Se…	Curated	Algorithms	`AIMech:MochaSystemsAwarePrimalDualFederatedMultiTaskLearning`	4 claims 3 sources
Mode Confusion Bias An individual bias occurring when modal interfaces confuse human operators causing actions appropriate for a different mode but incorrect fo…	AIO	Bias	`AIO:ModeConfusionBias`	Imported
Model An abstract representation of a complex system generally assembled as a set of logical mathematical or conceptual properties to simulate or…	AIO	Model	`AIO:Model`	Imported
Model Selection Bias A processing bias introduced when using data to select a single "best" model from many or when an explanatory variable has a weak relationsh…	AIO	Bias	`AIO:ModelSelectionBias`	Imported
Model-free regression functionals, regressor-reweighting well-specification diagnostic, and M-of-N XY-bootstrap sandwich limit aka Models as Approximations II model-free theory of parametric regression (Buja, Brown, Kuchibhotla, Berk, George, & Zhao 2019), Regressor-only Gaussian reweighting diagnostic trace and bootstrap tilt test for well-specification… A general model-free theory and diagnostic framework for parametric and penalized regression estimators viewed as statistical functionals th…	Curated	Mathematical Methods	`AIMech:ModelFreeRegressionFunctionalsReweightingDiagnosticAndXYBootstrapLimit`	4 claims 3 sources
Model-robust nonlinearity-consistent sandwich variance and Ratio of Asymptotic Variances (RAV) specification test aka Models as Approximations I model-robust linear regression framework (Buja et al. 2019), Ratio of Asymptotic Variances (RAV_j) regressor-specific misspecification diagnostic and test… A model-robust theory and diagnostic methodology for ordinary least squares (OLS) linear regression under arbitrary joint regressor-response…	Curated	Mathematical Methods	`AIMech:ModelRobustNonlinearityConsistentSandwichAndRAVSpecificationTest`	4 claims 3 sources
Model-X anytime-valid conditional independence testing via e-processes aka Model-X Conditional Independence E-Statistics, Sequential E-CRT (e-Conditional Randomization Test)… A sequential conditional independence testing framework (Grünwald, Henzi, & Lardy 2024, Journal of the American Statistical Association 119(…	Curated	Mathematical Methods	`AIMech:ModelXAnytimeValidConditionalIndependenceTesting`	4 claims 4 sources
Modified Connectionist Q-Learning The original neural action-value learning procedure that uses a selected-next-action temporal-difference error to update weights through acc…	Curated	Algorithms	`AIMech:ModifiedConnectionistQLearning`	6 claims 1 source
MoDIR Momentum Adversarial Domain Invariant Representation Learning for Zero-Shot Dense Retrieval aka MoDIR, Momentum Adversarial Domain Invariant Representation Learning… An unsupervised domain adaptation algorithm for zero-shot dense text retrieval (ZeroDR) that transfers a dual-encoder g(; theta_g) from a la…	Curated	Algorithms	`AIMech:MoDIRMomentumAdversarialDomainInvariantDenseRetrieval`	4 claims 3 sources
Modular Language Model aka Modular LM A language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve complex…	AIO	Model	`AIO:ModularLanguageModel`	Imported
Modular LLM aka Modular Large Language Model, component skills… A modular language model that consists of multiple specialized components or skills that can be dynamically composed and recombined to solve…	AIO	Model	`AIO:ModularLLM`	Imported
MoLE (Mixture of LoRA Experts) aka Mixture of LoRA Experts, MoLE Hierarchical LoRA Composition… A hierarchical modular composition architecture for pre-trained Low-Rank Adaptation (LoRA) modules that treats each layer of N frozen traine…	Curated	Architectures	`AIMech:MoLEMixtureOfLoRAExperts`	4 claims 3 sources
Momentum contrast aka MoCo A contrastive representation-learning mechanism that maintains a queue of encoded negative keys and produces new keys with an encoder update…	Curated	Algorithms	`AIMech:MomentumContrast`	1 claim 1 source
Moniqua Modulo Quantized Communication for Decentralized SGD aka Moniqua, Modulo Quantized Communication in Decentralized SGD… A zero-additional-memory communication-quantization algorithm for decentralized stochastic optimization (Moniqua) that exploits an a priori…	Curated	Algorithms	`AIMech:MoniquaModuloQuantizedCommunicationForDecentralizedSgd`	4 claims 3 sources
monoBERT and duoBERT Multi-Stage Document Ranking aka duoBERT, monoBERT and duoBERT… A three-stage cascading document ranking architecture (H_0 -> H_1 -> H_2) in which a bag-of-words BM25 stage H_0 retrieves top-k_0 candidate…	Curated	Architectures	`AIMech:DuoBERTMultiStageDocumentRankingWithBERT`	4 claims 3 sources
MonoT5: Document Ranking with a Pretrained Sequence-to-Sequence Model aka MonoT5 Pointwise Sequence-to-Sequence Reranker, T5 Target-Word Generation Document Ranking… A sequence-to-sequence pointwise document and passage reranking method (Nogueira, Jiang, Pradeep, & Lin, Findings of EMNLP 2020) that format…	Curated	Algorithms	`AIMech:MonoT5DocumentRankingWithPretrainedSeq2SeqModels`	3 claims 3 sources
Monotonic Gaussian process with virtual derivatives aka GP with monotonicity information, Gaussian process with monotonicity information A Gaussian-process inference procedure that promotes monotonicity in selected input coordinates by combining observed outputs with finite vi…	Curated	Algorithms	`AIMech:MonotonicGaussianProcessWithVirtualDerivatives`	4 claims 1 source
Monte Carlo Expectation Maximization aka MCEM, Monte Carlo EM An expectation-maximization method that approximates the current conditional expected complete-data log objective by Monte Carlo integration…	Curated	Algorithms	`AIMech:MonteCarloExpectationMaximization`	3 claims 1 source
MOOCdb Four-Mode Learner Interaction Schema and Multi-Layer Privacy Partitioning aka MOOCdb Standardized Relational Learner Telemetry Schema, MOOCdb Four-Mode Behavioral Interaction and Three-Layer User Anonymization Framework A cross-platform data standardization, feature-engineering, and privacy-partitioning preprocessing method for Massive Open Online Course (MO…	Curated	Preprocessing Methods	`AIMech:MOOCdbFourModeLearnerInteractionSchemaAndMultiLayerPrivacyPartitioning`	4 claims 3 sources
MOON (Model-Contrastive Federated Learning) aka MOON, Model-Contrastive Federated Learning… A federated learning algorithm for non-IID data (Li, He, & Song 2021, Algorithm 1) that corrects local representation drift by augmenting ea…	Curated	Algorithms	`AIMech:MoonModelContrastiveFederatedLearning`	4 claims 3 sources
MoRA aka MoRA High-Rank Updating, Square-Matrix High-Rank Parameter-Efficient Fine-Tuning A parameter-efficient fine-tuning algorithm that replaces the pair of rectangular low-rank adapter matrices in LoRA with a single trainable…	Curated	Algorithms	`AIMech:MoRA`	4 claims 3 sources
MORES (Modularized Transformer-Based Ranking Framework) aka MORES, MOdualarized REranking System… A modularized Transformer-based document reranking architecture (Gao, Dai, & Callan, EMNLP 2020; initially introduced as EARL in arXiv:2004.…	Curated	Architectures	`AIMech:MORESModularizedTransformerBasedRankingFramework`	4 claims 3 sources
Moshpit SGD and Moshpit All-Reduce aka Moshpit SGD, Moshpit All-Reduce… A fault-tolerant, communication-efficient decentralized averaging protocol (Moshpit All-Reduce, Algorithm 1) and distributed local stochasti…	Curated	Algorithms	`AIMech:MoshpitSgdAndMoshpitAllReduceForFaultTolerantDecentralizedTraining`	4 claims 3 sources
MPT (Multitask Prompt Tuning) aka Multitask Prompt Tuning, MPT Prompt Decomposition and Distillation… A parameter-efficient multitask prompt transfer methodology for frozen pre-trained language models that decomposes each task's soft prompt m…	Curated	Algorithms	`AIMech:MPTMultitaskPromptTuning`	4 claims 3 sources
MREC A recursive heuristic search algorithm that retains an explicit search graph within available additional memory, explores unstored successor…	Curated	Algorithms	`AIMech:MREC`	4 claims 1 source
MSDA and SSDA (Multi-Step and Single-Step Dual Accelerated Decentralized Optimization) aka MSDA and SSDA, Multi-Step Dual Accelerated Decentralized Optimization… Rate-optimal decentralized optimization algorithms for alpha-strongly convex and beta-smooth objectives min_{theta_1=...=theta_n} sum_{i=1}^…	Curated	Algorithms	`AIMech:MsdaMultiStepDualAcceleratedDecentralizedOptimization`	4 claims 3 sources
Multi-class N-pair loss aka N-pair-mc loss A supervised metric-learning objective that averages a joint positive-versus-multiple-negative log-softmax loss across a batch of positive p…	Curated	Mathematical Methods	`AIMech:MultiClassNPairLoss`	1 claim 1 source
Multi-label text mixture model A generative multi-label document model that selects a label subset and a mixture supported on that subset, then generates each word through…	Curated	Model Families	`AIMech:MultiLabelTextMixtureModel`	2 claims 1 source
Multi-task Bayesian optimization The original Swersky–Snoek–Adams 2013 family of Bayesian optimization procedures that uses a Gaussian process with separable finite-task and…	Curated	Algorithms	`AIMech:MultiTaskBayesianOptimization`	6 claims 1 source
Multi-Task LLM aka Multi-Task Large Language Model, transfer learning A large language model which is trained jointly on multiple language tasks simultaneously, learning shared representations that transfer acr…	AIO	Model	`AIO:MultiTaskLLM`	Imported
Multiclass Classification aka Multinomial Classification A classification focused on methods that classify instances into one of three or more classes.	AIO	MachineLearningTask	`AIO:MulticlassClassification`	Imported
Multiclass Multiple Kernel Maximum Margin Clustering aka Multi-Class Multiple Kernel Clustering A multiclass unsupervised clustering procedure that jointly fits shared nonnegative multiple-kernel weights and latent class-score functions…	Curated	Algorithms	`AIMech:MulticlassMultipleKernelMaximumMarginClustering`	4 claims 1 source
Multidimensional Scaling aka MDS A dimensionality reduction method that translates information about the pairwise distances among a set of objects or individuals into a conf…	AIO	MachineLearningTask	`AIO:MultidimensionalScaling`	Imported
MultiHeadAttention Layer An attention layer that allows the model to attend to information from different representation subspaces.	AIO	Layer	`AIO:MultiHeadAttentionLayer`	Imported
Multilingual LLM aka Multilingual Large Language Model, cross-lingual transfer A large language model that is trained on text from multiple languages learning shared representations that enable zero-shot or few-shot tra…	AIO	Model	`AIO:MultilingualLLM`	Imported
Multimodal Deep Learning A deep neural network that processes and links information using various modalities.	AIO	Network	`AIO:MultimodalDeepLearning`	Imported
Multimodal Fusion LLM aka cross-modal grounding A large language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for…	AIO	Model	`AIO:MultimodalFusionLLM`	Imported
Multimodal Language Model aka Mulimodal LM A language model that learns joint representations across different modalities like text vision and audio in an end-to-end fashion for bette…	AIO	Model	`AIO:MultimodalLanguageModel`	Imported
Multimodal Learning A machine learning task that uses multiple modalities of data such as text audio and images to improve learning outcomes.	AIO	MachineLearningTask	`AIO:MultimodalLearning`	Imported
Multimodal LLM aka Multimodal Large Language Model, cross-modal grounding A multimodal large language model that learns joint representations across different modalities like text vision and audio in an end-to-end…	AIO	Model	`AIO:MultimodalLLM`	Imported
Multimodal Prompt-based Language Model A multimodal large language model which processes prompts that include multiple modalities, such as both text and images, to generate releva…	AIO	Model	`AIO:MultimodalPromptbasedLanguageModel`	Imported
Multimodal Transformer aka unified encoder, vision-language model A transformer network that processes and relates information from different modalities such as text images and audio using a shared embeddin…	AIO	Network	`AIO:MultimodalTransformer`	Imported
Multiple-testing node conflict diagnostic A Bayesian evidence-synthesis diagnostic that partitions information at replicated separator nodes, stacks declared contrasts between transf…	Curated	Algorithms	`AIMech:MultipleTestingNodeConflictDiagnostic`	7 claims 3 sources
Multiple-try Metropolis aka MTM A Metropolis sampling algorithm that selects a candidate from several weighted forward proposals, draws a backward reference set containing…	Curated	Algorithms	`AIMech:MultipleTryMetropolis`	1 claim 1 source
Multiple-try Metropolis within Gibbs aka MTM-Gibbs, Griddy Gibbs multiple-try Metropolis A coordinate-update sampler that applies a multiple-try Metropolis transition to a conditional target while holding all other coordinates fi…	Curated	Algorithms	`AIMech:MultipleTryMetropolisWithinGibbs`	1 claim 1 source
Multiply Layer A merging layer that multiplies (element-wise) a list of inputs.	AIO	Layer	`AIO:MultiplyLayer`	Imported
Multiview Kernel K-Means aka MVKKM A multiview clustering algorithm that alternates kernel k-means on a power-weighted combination of fixed view kernels with simplex view-weig…	Curated	Algorithms	`AIMech:MultiviewKernelKMeans`	6 claims 1 source
Multiway Karmarkar–Karp differencing A multiway number-partitioning heuristic that represents partial partitions by normalized bin-load vectors and repeatedly combines two selec…	Curated	Algorithms	`AIMech:MultiwayKarmarkarKarpDifferencing`	6 claims 2 sources
Muon optimizer aka Muon A neural-network optimization method that approximately orthogonalizes momentum-based matrix updates using Newton–Schulz iterations.	Curated	Algorithms	`AIMech:Muon`	1 claim 1 source
Mutual information neural estimation aka MINE, Mutual information neural estimator A mutual-information estimation procedure that trains a neural statistics function to maximize a Donsker–Varadhan objective contrasting join…	Curated	Algorithms	`AIMech:MutualInformationNeuralEstimation`	1 claim 3 sources
NAdam aka Nesterov-accelerated adaptive moment estimation An Adam-family optimizer combining adaptive moment scaling with a Nesterov-style momentum update.	Curated	Algorithms	`AIMech:NAdam`	1 claim 1 source
Naive Bayes aka Naive Bayesian classifier Probabilistic classification assuming feature independence conditional on the class.	Curated	Model Families	`AIMech:NaiveBayes`	1 claim 1 source
NASNet Scheduled DropPath A NASNet training regularizer that stochastically suppresses operation-bearing edges within convolutional cells using a drop probability tha…	Curated	Algorithms	`AIMech:NASNetScheduledDropPath`	6 claims 1 source
Natasha 2 Non-Convex Stochastic Optimization via Swing-by Saddle Points aka Natasha 2, Natasha 2 Algorithm… A stochastic non-convex optimization method (Allen-Zhu 2018) for online or large-scale objectives f(x) = E_i[f_i(x)] with L-Lipschitz gradie…	Curated	Algorithms	`AIMech:Natasha2NonconvexStochasticOptimizationViaSwingBySaddlePoints`	3 claims 3 sources
Natural Compression and Natural Dithering for Distributed Optimization aka Natural Compression, Natural Dithering… A family of unbiased power-of-two randomized quantization operators for distributed and in-network gradient aggregation (Horváth et al. 2022…	Curated	Algorithms	`AIMech:NaturalCompressionAndNaturalDitheringForDistributedOptimization`	4 claims 3 sources
Natural Evolution Strategies aka NES A family of black-box optimization algorithms that adapts a parameterized search distribution using estimates of the natural gradient of exp…	Curated	Algorithms	`AIMech:NaturalEvolutionStrategies`	1 claim 1 source
Natural gradient A metric-dependent differential method that maps the coordinate derivatives of a differentiable objective to a tangent vector by the inverse…	Curated	Mathematical Methods	`AIMech:NaturalGradient`	6 claims 3 sources
Natural Language Processing aka NLP A machine learning task focused on the interactions between computers and human language including programming computers to process and anal…	AIO	MachineLearningTask	`AIO:NaturalLanguageProcessing`	Imported
Neal backtracking-suppressed MCMC A finite-state MCMC construction that augments a reversible chain with its preceding state and replaces a conditional resampling step with a…	Curated	Algorithms	`AIMech:NealBacktrackingSuppressedMCMC`	6 claims 2 sources
Nearest-neighbor distance-norm data description aka Nearest neighbor domain description (Angiulli), NNDD distance-norm rule A one-class decision rule that forms the ordered distances from a query to its first k reference neighbors and accepts the query when the L_…	Curated	Algorithms	`AIMech:NearestNeighborDistanceNormDataDescription`	4 claims 2 sources
Nearest-neighbor ratio data description aka Nearest neighbor distance ratio data description, Nearest-neighbor data description (Tax-Duin) A target-class data-description algorithm that scores a query by its distance to a nearest reference observation divided by that observation…	Curated	Algorithms	`AIMech:NearestNeighborRatioDataDescription`	4 claims 2 sources
Nearest-neighbor-chain clustering aka Nearest neighbor chain algorithm, NN-chain clustering An agglomerative clustering algorithm that follows a chain of nearest clusters until its last pair are reciprocal nearest neighbors, merges…	Curated	Algorithms	`AIMech:NearestNeighborChainClustering`	6 claims 7 sources
NEFTune aka Noisy Embedding Instruction Finetuning, NEFT Noisy Embedding Finetuning… A regularization algorithm for language model instruction fine-tuning that perturbs input token embedding tensors X_emb in R^{B x L x d} dur…	Curated	Algorithms	`AIMech:NEFTune`	4 claims 3 sources
Neighbourhood components analysis aka Neighborhood components analysis, NCA A supervised metric-learning algorithm that learns a linear transformation by maximizing the expected number of correctly classified trainin…	Curated	Algorithms	`AIMech:NeighborhoodComponentsAnalysis`	1 claim 1 source
Nested antithetic modification A finite conditional transition construction that starts with independent draws from the conditional distribution and successively applies m…	Curated	Algorithms	`AIMech:NestedAntitheticModification`	6 claims 1 source
Nested Lasso Adaptive Banding for Covariance Estimation aka Adaptive Cholesky Banding via Nested Lasso Penalty, Levina-Rothman-Zhu Nested Lasso Modified Cholesky Covariance Estimator… Nested Lasso Adaptive Banding for Covariance Estimation is a high-dimensional covariance and precision matrix regularization method for natu…	Curated	Mathematical Methods	`AIMech:NestedLassoAdaptiveBandingForCovarianceEstimation`	3 claims 3 sources
Network A system of interconnected nodes or entities for communication, computation or data exchange.	AIO	Network	`AIO:Network`	Imported
Neural autoregressive distribution estimator aka NADE A fully visible autoregressive density model whose ordered variable conditionals are computed by neural networks that share input-to-hidden…	Curated	Architectures	`AIMech:NeuralAutoregressiveDistributionEstimator`	1 claim 1 source
Neural GPU aka Neural GPUs A recurrent neural architecture that embeds a complete symbolic sequence in a spatial state grid and repeatedly applies shared convolutional…	Curated	Architectures	`AIMech:NeuralGPU`	6 claims 2 sources
Neural network pushdown automaton aka NNPDA A recurrent state-controller architecture whose signed action output pushes or removes fractional quantities of input symbols on an external…	Curated	Architectures	`AIMech:NeuralNetworkPushdownAutomaton`	6 claims 1 source
Neural probabilistic language model aka NPLM A neural finite-context language architecture that jointly learns a shared word-embedding lookup and a nonlinear predictor of the next-word…	Curated	Architectures	`AIMech:NeuralProbabilisticLanguageModel`	1 claim 1 source
Neural Turing Machine Network aka NTM A deep feedforward network that combines neural network pattern matching with the algorithmic power of programmable computers.	AIO	Network	`AIO:NeuralTuringMachineNetwork`	Imported
Neural variational inference and learning aka NVIL A method for jointly training a directed latent-variable model and an amortized stochastic inference network by maximizing a variational log…	Curated	Algorithms	`AIMech:NeuralVariationalInferenceAndLearning`	3 claims 2 sources
Neuro-Symbolic LLM aka Neuro-Symbolic Large Language Model, knowledge reasoning… A large language model which combines neural language modeling with symbolic reasoning components, leveraging structured knowledge represent…	AIO	Model	`AIO:NeuroSymbolicLLM`	Imported
Newman greedy modularity algorithm aka Newman fast community detection, Newman agglomerative modularity Newman’s direct edge-fraction-matrix algorithm for greedy agglomerative community detection, which starts with singleton vertices, joins adj…	Curated	Algorithms	`AIMech:NewmanGreedyModularity`	7 claims 2 sources
Newman random-walk betweenness matrix computation aka Newman matrix algorithm for random-walk betweenness An exact network-analysis algorithm that computes random-walk betweenness from an embedded inverse of a grounded graph Laplacian, explicitly…	Curated	Algorithms	`AIMech:NewmanRandomWalkBetweennessMatrix`	6 claims 2 sources
Newton Sketch Randomized Hessian-Projected Second-Order Optimization and Sketched Interior-Point Barrier Method aka Newton Sketch (Pilanci & Wainwright 2017), Sketched Newton Method with Tangent-Cone Gaussian Width Guarantees… Newton Sketch Randomized Hessian-Projected Second-Order Optimization and Sketched Interior-Point Barrier Method is a randomized second-order…	Curated	Mathematical Methods	`AIMech:NewtonSketchRandomizedHessianProjectedOptimization`	3 claims 3 sources
NeXO ontology alignment aka AlignOntology An iterative ontology-alignment algorithm that combines shared-terminal set overlap with parent and child neighborhood similarities, then gr…	Curated	Algorithms	`AIMech:NeXOOntologyAlignment`	5 claims 1 source
NeXO ontology construction aka NeXO construction algorithm A network-based ontology-construction procedure that starts from a probabilistic hierarchy of gene communities, removes unsupported binary r…	Curated	Algorithms	`AIMech:NeXOOntologyConstruction`	6 claims 2 sources
Nguyen–Wainwright–Jordan variational bound aka NWJ bound, MINE-f objective… A variational lower bound on Kullback–Leibler divergence that subtracts a product-distribution exponential critic moment from a joint-distri…	Curated	Mathematical Methods	`AIMech:NguyenWainwrightJordanBound`	1 claim 2 sources
NIDS (Network-Independent Step-Size Decentralized Proximal-Gradient Method) aka NIDS, Network-Independent Step-Size Decentralized Proximal-Gradient Method… A decentralized composite optimization algorithm (Li, Shi, & Yan 2019, Section II, Equation 4) for minimizing (1/n) sum_{i=1}^n (s_i(x) + r_…	Curated	Algorithms	`AIMech:NidsNetworkIndependentStepSizeDecentralizedProximalGradientMethod`	4 claims 3 sources
No-U-Turn sampler (original slice formulation) The original 2014 slice-based NUTS algorithm, which adapts a Hamiltonian trajectory’s length through randomly directed binary-tree doubling…	Curated	Algorithms	`AIMech:OriginalNoUTurnSampler`	2 claims 2 sources
NOAH (Neural Prompt Search) aka Neural Prompt Search, NOAH One-Shot Neural Prompt Architecture Search… A one-shot neural architecture search (NAS) parameter-efficient tuning methodology for large vision models that embeds Visual Prompt Tuning…	Curated	Algorithms	`AIMech:NOAHNeuralPromptSearch`	4 claims 3 sources
node2vec aka N2V A machine learning task designed to learn continuous feature representations for nodes in a graph by optimizing a neighborhood-preserving ob…	AIO	MachineLearningTask	`AIO:node2vec`	Imported
node2vec-CBOW aka N2V-CBOW, CBOW A node2vec that predicts the current node from a window of surrounding context nodes, with the order of context nodes not influencing predic…	AIO	MachineLearningTask	`AIO:node2vecCBOW`	Imported
node2vec-SkipGram aka N2V-SkipGram, SkipGram A node2vec that uses the current node to predict the surrounding window of context nodes, weighing nearby context nodes more heavily than di…	AIO	MachineLearningTask	`AIO:node2vecSkipGram`	Imported
Noh–Rieger random-walk centrality aka Random walk centrality of Noh and Rieger A node-scoring method for an undirected random walk that divides each node’s stationary visitation probability by its integrated excess retu…	Curated	Mathematical Methods	`AIMech:NohRiegerRandomWalkCentrality`	6 claims 1 source
Noise Dense Layer A layer that is a densely-connected neural network layer with added noise for regularization.	AIO	Layer	`AIO:NoiseDenseLayer`	Imported
Noisy Channel Language Model Prompting aka Noisy Channel Prompting, Channel Prompt Tuning… A few-shot language model prompting and prompt-tuning method for text classification that applies Bayes' rule under a uniform class prior P(…	Curated	Algorithms	`AIMech:NoisyChannelLanguageModelPrompting`	4 claims 3 sources
Noisy Input Layer An input layer that adds noise to each value.	AIO	Layer	`AIO:NoisyInputLayer`	Imported
Noisy Power Method for Perturbed Subspace Iteration, Streaming PCA, and Differentially Private Spectral Analysis aka Hardt-Price Noisy Power Method (NPM), Streaming Power Method (SPM) and Private Power Method (PPM)… The Noisy Power Method (NPM) for Perturbed Subspace Iteration, Streaming PCA, and Differentially Private Spectral Analysis is a meta-algorit…	Curated	Algorithms	`AIMech:NoisyPowerMethodForStreamingAndDifferentiallyPrivatePCA`	3 claims 3 sources
Noisy rectifier A stochastic activation that adds zero-mean noise to a preactivation and then applies the positive-part rectifier, producing h=max(0,a+z).	Curated	Mathematical Methods	`AIMech:NoisyRectifier`	1 claim 1 source
Noisy-OR belief network A directed acyclic binary probabilistic network that models a node’s inactivity as the product of a leak-failure factor and failure factors…	Curated	Architectures	`AIMech:NoisyORBeliefNetwork`	1 claim 1 source
NOLA aka NOLA (Compressing LoRA Using Linear Combination of Random Basis), Random-Basis Bilinear Low-Rank Adaptation… A parameter-efficient fine-tuning and model-compression method that overcomes the rank-one parameter lower bound of Low-Rank Adaptation (LoR…	Curated	Algorithms	`AIMech:NOLA`	4 claims 3 sources
Non-Backtracking Walk Matrix and Kesten-Stigum Spectral Redemption aka Non-Backtracking Matrix Spectral Clustering, Hashimoto Non-Backtracking Operator Spectral Redemption… Non-Backtracking Walk Matrix and Kesten-Stigum Spectral Redemption is a spectral graph clustering framework introduced by Krzakala, Moore, M…	Curated	Algorithms	`AIMech:NonBacktrackingWalkMatrixAndKestenStigumSpectralRedemption`	3 claims 3 sources
Non-conjugate variational message passing aka NCVMP An approximate inference algorithm that restricts variational blocks to exponential families and updates their natural parameters by matchin…	Curated	Algorithms	`AIMech:NonconjugateVariationalMessagePassing`	7 claims 3 sources
Non-local block aka Non-local neural-network block A neural-network component that aggregates input-dependent pairwise contributions from positions across a representation, projects the aggre…	Curated	Layers & Modules	`AIMech:NonLocalBlock`	1 claim 1 source
Non-local means A classical image-denoising algorithm that estimates each pixel by a normalized average of observed pixel values, assigning exponential simi…	Curated	Algorithms	`AIMech:NonLocalMeans`	5 claims 1 source
Nonconcave Penalized Quasi-Likelihood for Sparse Covariance and Precision Matrix Estimation aka Lam-Fan Sparsistent Nonconcave Penalized Covariance and Precision Estimator, Folded-Concave SCAD/Hard-Thresholding Penalized Gaussian Quasi-Likelihood Covariance Selection… Nonconcave Penalized Quasi-Likelihood for Sparse Covariance and Precision Matrix Estimation is a unified high-dimensional estimation and sup…	Curated	Mathematical Methods	`AIMech:NonconcavePenalizedQuasiLikelihoodForSparseCovarianceAndPrecisionMatrixEstimation`	3 claims 3 sources
Nonconvex Matrix Completion Optimization Landscape Without Spurious Local Minima aka No Spurious Local Minima in Nonconvex Matrix Completion, Ge-Lee-Ma Strict-Saddle Landscape for Factored Matrix Completion… A global nonconvex optimization landscape characterization (introduced by Rong Ge, Jason D. Lee, and Tengyu Ma in 2016) proving that the Bur…	Curated	Mathematical Methods	`AIMech:NonconvexMatrixCompletionLandscapeWithoutSpuriousLocalMinima`	3 claims 3 sources
Nonlinear autoregressive model with exogenous inputs aka NARX model, Nonlinear autoregressive exogenous model A discrete-time nonlinear input-output model family whose current output is a function of finite lagged outputs and exogenous inputs, plus a…	Curated	Model Families	`AIMech:NonlinearAutoregressiveExogenousModel`	6 claims 2 sources
Nonlinear autoregressive moving average model with exogenous inputs aka NARMAX model A discrete-time nonlinear input-output model family whose current output is a function of finite lagged outputs, exogenous inputs and errors…	Curated	Model Families	`AIMech:NonlinearAutoregressiveMovingAverageExogenousModel`	6 claims 2 sources
Nonnegative Matrix Factorization aka NMF A matrix-decomposition method that represents or approximates a nonnegative data matrix as the product of two entrywise nonnegative factor m…	Curated	Mathematical Methods	`AIMech:NonnegativeMatrixFactorization`	3 claims 1 source
Nonparametric Bayes pachinko allocation model aka NPB PAM, nonparametric PAM A Bayesian pachinko topic-model family using coupled hierarchical Dirichlet-process allocations to infer occupied supertopics and shared sub…	Curated	Model Families	`AIMech:NonparametricBayesPachinkoAllocationModel`	3 claims 1 source
Nonparametric two-sample testing by betting aka Sequential IPM Two-Sample Testing by Betting, ONS-Predicted Witness Two-Sample Betting Test… A general sequential nonparametric two-sample and operator-invariance hypothesis testing framework (Shekhar & Ramdas 2023, IEEE Transactions…	Curated	Mathematical Methods	`AIMech:NonparametricTwoSampleTestingByBetting`	4 claims 3 sources
Nonreversible Metropolis uniform update A Metropolis transition algorithm that retains a signed uniform acceptance variable, updates it by wrapped translation, and rescales it afte…	Curated	Algorithms	`AIMech:NonreversibleMetropolisUniformUpdate`	6 claims 1 source
Nonsmooth Convex-Composite Optimization, Weak Convexity, Sharpness, and Prox-Linear Low-Rank Matrix Recovery aka Convex-Composite Low-Rank Matrix Recovery, Weakly Convex and Sharp Nonsmooth Low-Rank Matrix Estimation… A unified nonsmooth convex-composite optimization framework (introduced by Vasileios Charisopoulos, Yudong Chen, Damek Davis, Mateo Díaz, Li…	Curated	Mathematical Methods	`AIMech:NonsmoothCompositeOptimizationAndProxLinearLowRankMatrixRecovery`	3 claims 3 sources
Norm-stabilizer aka Norm stabilization regularization, Norm-stabilizer regularization A recurrent-network regularization procedure that adds a penalty on the average squared change in Euclidean norm between successive selected…	Curated	Algorithms	`AIMech:NormStabilizer`	6 claims 1 source
Normalization A data preparation that transforms data into a standard format or scale typically to reduce redundancy and improve consistency often involvi…	AIO	Preprocessing	`AIO:Normalization`	Imported
Normalization Layer A numerical features preprocessing layer that normalizes continuous features.	AIO	Layer	`AIO:NormalizationLayer`	Imported
Normalized temperature-scaled cross entropy loss aka NT-Xent, NT-Xent loss A contrastive cross-entropy objective that uses cosine-normalized, temperature-scaled similarities to identify a paired positive representat…	Curated	Mathematical Methods	`AIMech:NTXentLoss`	2 claims 2 sources
Nostalgic Adam aka NosAdam, NosAdam-HH Hyperharmonic Second-Moment Adaptive Optimization… An adaptive first-order stochastic optimization algorithm that replaces Adam's constant second-moment decay parameter beta_2 with a schedule…	Curated	Algorithms	`AIMech:NosAdam`	4 claims 3 sources
Novelty SAT heuristic aka Novelty A clause-based SAT local-search heuristic that ranks candidate flips by total violation count with oldest-variable tie breaks, normally sele…	Curated	Algorithms	`AIMech:Novelty`	2 claims 2 sources
Novelty+ SAT heuristic aka Novelty+ A Novelty extension that, at each SAT search step, chooses a random variable from a randomly selected unsatisfied clause with a fixed walk p…	Curated	Algorithms	`AIMech:NoveltyPlus`	2 claims 2 sources
NovoGrad A stochastic gradient optimizer that rescales each parameter block gradient by a scalar running second moment of that block gradient norm be…	Curated	Algorithms	`AIMech:NovoGrad`	7 claims 3 sources
Nu support vector classification aka Nu-SVC, ν-SVC… A supervised binary-classification algorithm that jointly fits a regularized kernel hyperplane and a nonnegative margin level, using nu to r…	Curated	Algorithms	`AIMech:NuSupportVectorClassification`	7 claims 1 source
Nu support vector regression aka Nu-SVR, ν-SVR… A supervised regression algorithm that jointly fits a regularized kernel expansion and a nonnegative constant epsilon-insensitive tube half-…	Curated	Algorithms	`AIMech:NuSupportVectorRegression`	7 claims 1 source
Numerical Features Preprocessing Layer A layer that performs numerical data preprocessing operations.	AIO	Layer	`AIO:NumericalFeaturesPreprocessingLayer`	Imported
Nyström Gram Matrix Low-Rank Approximation with Diagonal Sampling aka Drineas-Mahoney Nyström Gram Matrix Approximation, Column-Sampled Rank-k Nyström Kernel Approximation… Nyström Gram Matrix Low-Rank Approximation with Diagonal Sampling is a randomized low-rank kernel approximation algorithm analyzed by Drinea…	Curated	Algorithms	`AIMech:NystromGramMatrixLowRankApproximationWithDiagonalSampling`	3 claims 3 sources
O-LoRA aka Orthogonal Low-Rank Adaptation, O-LoRA Continual Subspace Learning… A rehearsal-free continual learning algorithm for pretrained language models that allocates a low-rank adapter pair (A_t, B_t) for each sequ…	Curated	Algorithms	`AIMech:OLoRA`	4 claims 3 sources
Oblivious Sparse Norm-Approximating Projections (OSNAP) for Fast Numerical Linear Algebra aka OSNAP, Oblivious Sparse Norm-Approximating Projection… An Oblivious Sparse Norm-Approximating Projection (OSNAP) is a distribution over sparse sketching matrices Pi in {0, +1/sqrt(s), -1/sqrt(s)}…	Curated	Mathematical Methods	`AIMech:ObliviousSparseNormApproximatingProjectionsForNumericalLinearAlgebra`	3 claims 3 sources
Oja Learning Rule aka Oja’s Rule A single-output linear-neuron learning rule that combines a Hebbian input-output weight increment with an output-squared weight decay, obtai…	Curated	Algorithms	`AIMech:OjaLearningRule`	4 claims 1 source
Oja's Streaming PCA Algorithm with Matrix-Bernstein-Matching Finite-Sample Guarantees aka Jain-Jin-Kakade-Netrapalli-Sidford Oja Streaming PCA Analysis, Matrix-Product Operator Analysis of Oja's Streaming PCA Algorithm… Oja's Streaming PCA Algorithm with Matrix-Bernstein-Matching Finite-Sample Guarantees is a single-pass O(d)-space, linear-time streaming eig…	Curated	Algorithms	`AIMech:StreamingPCANearOptimalFiniteSampleOjaAlgorithm`	3 claims 3 sources
OLS post-Lasso and fitness-thresholded post-model selection estimation aka Gauss-Lasso and OLS Post-Fit Lasso High-Dimensional Sparse Regression, OLS Post-Model Selection with Sublinear Restricted Sparse Eigenvalue Sparsity Bounds… OLS post-Lasso and fitness-thresholded post-model selection estimation are a nonasymptotic two-step high-dimensional nonparametric regressio…	Curated	Mathematical Methods	`AIMech:OLSPostLassoAndFitnessThresholdedPostModelSelectionEstimation`	4 claims 3 sources
OLS Post-Lasso and Fitness-Thresholded Post-Model-Selection Estimation in High-Dimensional Sparse Models aka OLS Post-Lasso, Least Squares Post-Lasso… A two-stage high-dimensional sparse regression methodology and non-asymptotic oracle rate theory (introduced by Alexandre Belloni and Victor…	Curated	Algorithms	`AIMech:OLSPostLassoAndFitnessThresholdedPostModelSelectionInHighDimensionalSparseModels`	3 claims 3 sources
One-class support vector machine aka OCSVM, One-class SVM… A support-estimation algorithm that optimizes a kernel feature-space score relative to the origin using a norm penalty, a learned offset and…	Curated	Algorithms	`AIMech:OneClassSupportVectorMachine`	8 claims 1 source
One-shot Learning aka OSL A deep neural network that classifies objects from one or only a few examples.	AIO	Network	`AIO:OneshotLearning`	Imported
One-stage and two-stage adaptive step-up procedures for false discovery rate control under independence and dependence aka Blanchard-Roquain One-Stage and Two-Stage Adaptive Step-Up FDR Procedures, BR-1S-lambda and BR-2S-lambda Adaptive Step-Up FDR Procedures… A family of one-stage and two-stage adaptive multiple hypothesis testing procedures developed by Gilles Blanchard and Etienne Roquain (2009,…	Curated	Mathematical Methods	`AIMech:OneAndTwoStageAdaptiveStepUpFDRUnderDependence`	4 claims 2 sources
One-vs-one N-pair loss aka N-pair-ovo loss A supervised metric-learning objective that sums separate positive-versus-negative softplus comparisons for each anchor in a batch of positi…	Curated	Mathematical Methods	`AIMech:OneVsOneNPairLoss`	1 claim 1 source
Online hybrid temporal regression planning An online planning-and-scheduling procedure that plans successive jobs by goal-regression A* over logical conditions, variable bindings, sha…	Curated	Algorithms	`AIMech:OnlineHybridTemporalRegressionPlanning`	8 claims 2 sources
Operator-Norm Consistent Estimation of Beta-Sparse Covariance Matrices aka El Karoui Beta-Sparse Covariance Hard-Thresholding Estimator, Graph-Walk Beta-Sparsity Operator-Norm Consistent Covariance Estimation… Operator-Norm Consistent Estimation of Beta-Sparse Covariance Matrices is a permutation-equivariant high-dimensional covariance and correlat…	Curated	Mathematical Methods	`AIMech:OperatorNormConsistentEstimationOfBetaSparseCovarianceMatrices`	3 claims 3 sources
OPTICS aka Ordering Points To Identify the Clustering Structure Density-based clustering analysis that orders observations using reachability across neighborhood scales.	Curated	Algorithms	`AIMech:OPTICS`	1 claim 1 source
OPTICS outlier factor aka OPTICS-OF, OPTICS with outlier factors An unsupervised local outlier-scoring procedure that uses self-inclusive, tie-inclusive nearest neighborhoods to compute inverse mean neighb…	Curated	Algorithms	`AIMech:OPTICSOutlierFactor`	7 claims 8 sources
Optimal multi-weighted step-up procedure for false discovery rate control aka Optimal Multi-Weighted Step-Up Procedure SU(W*), Damped Multi-Weighted Step-Up and Step-Down Procedures SU(W_tilde) and SD(W_tilde)… A step-wise multiple hypothesis testing methodology (Roquain & van de Wiel 2009, Electronic Journal of Statistics 3:678-711, arXiv:0807.4081…	Curated	Mathematical Methods	`AIMech:OptimalMultiWeightedStepUpProcedureForFDRControl`	4 claims 3 sources
Optimal Singular Value Hard Thresholding at 4/sqrt(3) for Low-Rank Matrix Denoising aka Gavish-Donoho 4/sqrt(3) Singular Value Hard Thresholding, Optimal Singular Value Hard Thresholding (SVHT)… A low-rank matrix denoising methodology introduced by Gavish and Donoho (2014, IEEE Transactions on Information Theory 60(8):5040-5053, arXi…	Curated	Mathematical Methods	`AIMech:OptimalSingularValueHardThresholdingAtFourOverSqrtThree`	3 claims 3 sources
Optimal Spjøtvoll and sieve-grouped p-value weighting aka Roeder-Wasserman Optimal and Grouped P-Value Weighting, Sieve-Principle Method-of-Moments Grouped P-Value Weighting… A frequentist family-wise error rate (FWER) p-value weighting and robustness framework developed by Kathryn Roeder and Larry Wasserman (2009…	Curated	Mathematical Methods	`AIMech:OptimalSpjotvollAndSieveGroupedPValueWeighting`	4 claims 3 sources
OptiPrompt Continuous Factual Probing aka OptiPrompt, OptiPrompt Continuous Prompt Factual Probing… A continuous prompt optimization and factual probing method for pretrained language models that replaces discrete template tokens with dense…	Curated	Algorithms	`AIMech:OptiPromptContinuousFactualProbing`	4 claims 3 sources
OptSpace (Degree Trimming, Rank-r Spectral Projection, and Grassmann Manifold Matrix Completion) aka OptSpace Matrix Completion Algorithm, Keshavan-Montanari-Oh Trimmed Spectral and Grassmann Manifold Matrix Completion… A three-stage spectral and Riemannian manifold algorithm (OptSpace, introduced by Raghunandan H. Keshavan, Andrea Montanari, and Sewoong O…	Curated	Algorithms	`AIMech:OptSpaceDegreeTrimmingSpectralProjectionAndGrassmannManifoldMatrixCompletion`	4 claims 3 sources
Order-agnostic NADE training aka Order-agnostic training of NADE A stochastic training procedure that shares neural conditional parameters across variable orderings and estimates the order-averaged NADE lo…	Curated	Algorithms	`AIMech:OrderAgnosticNADETraining`	1 claim 1 source
Ordinal LLM aka Ordinal Large Language Model, preference modeling… A large language model that is trained to model ordinal relationships and rank outputs rather than model probability distributions over text…	AIO	Model	`AIO:OrdinalLLM`	Imported
Orthogonal least squares forward selection aka Forward regression orthogonal least squares, FROLS A greedy fixed-candidate regression algorithm that repeatedly adds the column giving the largest reduction in squared residual after joint l…	Curated	Algorithms	`AIMech:OrthogonalLeastSquaresForwardSelection`	7 claims 3 sources
Orthogonal matching pursuit aka OMP A greedy fixed-dictionary approximation algorithm that selects an atom correlated with the current residual and recomputes the approximation…	Curated	Algorithms	`AIMech:OrthogonalMatchingPursuit`	6 claims 3 sources
Orthogonal Score and Weighted Double-Selection Post-Selection Inference in High-Dimensional Quantile Regression aka Orthogonal Score Quantile Regression Estimator, Weighted Double-Selection Quantile Regression… A post-selection inference methodology (introduced by Alexandre Belloni, Victor Chernozhukov, and Kengo Kato in 2019) for a target treatment…	Curated	Algorithms	`AIMech:OrthogonalScoreAndWeightedDoubleSelectionPostSelectionInferenceInHighDimensionalQuantileRegression`	3 claims 3 sources
Orthogonal Tensor Decomposition and Robust Tensor Power Method for Latent Variable Models aka Robust Tensor Power Method for Orthogonal Tensor Decomposition, Anandkumar-Ge-Hsu-Kakade-Telgarsky Tensor Method of Moments… A spectral and tensor-algebraic method-of-moments framework (introduced by Animashree Anandkumar, Rong Ge, Daniel Hsu, Sham M. Kakade, and M…	Curated	Algorithms	`AIMech:OrthogonalTensorDecompositionAndRobustTensorPowerMethodForLatentVariableModels`	4 claims 3 sources
Otsu thresholding aka Otsu’s method, Otsu threshold selection A histogram-based threshold-selection algorithm that partitions ordered gray levels by maximizing class-weighted between-class variance, equ…	Curated	Algorithms	`AIMech:OtsuThresholding`	1 claim 1 source
Output Layer A layer containing the last neurons in the network that produces given outputs for the program.	AIO	Layer	`AIO:OutputLayer`	Imported
Output-space Predictive Entropy Search A Bayesian global optimization algorithm that selects evaluations using an approximation to information about the latent maximum function va…	Curated	Algorithms	`AIMech:OutputSpacePredictiveEntropySearch`	6 claims 2 sources
Over-Specified Gaussian Mixture EM Singularity Dichotomy and Annulus-Based Epoch Localization aka Singular Over-Specified Gaussian Mixture EM Convergence Dichotomy, Annulus-Based Epoch Localization for Singular EM… A non-asymptotic statistical and algorithmic theory (introduced by Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Martin J. Wainwright, Michael I. J…	Curated	Mathematical Methods	`AIMech:OverSpecifiedGaussianMixtureEMSingularityAndAnnulusLocalization`	4 claims 3 sources
Overlapping hierarchical clustering (OHC) aka OHC clustering A graph-based agglomerative clustering algorithm that expands clusters across increasing distance thresholds when the change in induced edge…	Curated	Algorithms	`AIMech:OverlappingHierarchicalClustering`	6 claims 1 source
P-Tuning v2 Deep Continuous Prompt Tuning aka P-Tuning v2, PT-2 Deep Prompt Tuning for NLU… A parameter-efficient deep continuous prompt tuning method for natural language understanding and token-level sequence labeling that freezes…	Curated	Algorithms	`AIMech:PTuningV2DeepContinuousPromptTuning`	4 claims 3 sources
PABEE: Patience-Based Early Exit for Pretrained Language Models aka PABEE, Patience-Based Early Exit… An input-adaptive dynamic early-exit inference and training algorithm for deep neural networks and pre-trained language models that attaches…	Curated	Algorithms	`AIMech:PABEEPatienceBasedEarlyExitForBERT`	4 claims 3 sources
Pachinko allocation model aka PAM A topic-model family that generates each word by traversing a directed acyclic graph from a root through topic nodes to a word leaf, using p…	Curated	Model Families	`AIMech:PachinkoAllocationModel`	2 claims 1 source
Pachinko allocation topics over time model aka PAMTOT A topic-model family combining pachinko allocation paths with topic-specific continuous timestamp densities at multiple path levels, so that…	Curated	Model Families	`AIMech:PachinkoAllocationTopicsOverTimeModel`	3 claims 1 source
PaCMAP aka Pairwise Controlled Manifold Approximation Projection A nonlinear dimensionality-reduction algorithm that embeds neighbor, mid-near and farther point pairs using separate attractive and repulsiv…	Curated	Algorithms	`AIMech:PaCMAP`	1 claim 1 source
PACT (Parameterized Clipping Activation for Quantized Neural Networks) aka PACT, Parameterized Clipping Activation… PACT (Parameterized Clipping Activation for Quantized Neural Networks) is a quantization-aware activation clipping scheme that replaces unbo…	Curated	Algorithms	`AIMech:PACTParameterizedClippingActivationForQuantizedNeuralNetworks`	4 claims 3 sources
Padam Partially Adaptive Momentum Estimation Optimization aka Padam, Partially Adaptive Momentum Estimation… Partially Adaptive Momentum Estimation (Padam) is a first-order adaptive stochastic optimization algorithm (Chen, Zhou, Tang, Yang, Cao, & G…	Curated	Algorithms	`AIMech:PadamPartiallyAdaptiveMomentumEstimationOptimization`	4 claims 3 sources
PAGE (Probabilistic Gradient Estimator) for Non-Convex Optimization aka PAGE, Probabilistic Gradient Estimator… A single-loop (loopless) variance-reduced stochastic optimization algorithm and probabilistic gradient estimator (Li, Bao, Zhang, & Richtari…	Curated	Algorithms	`AIMech:PageProbabilisticGradientEstimatorForNonconvexOptimization`	3 claims 3 sources
PageRank aka PageRank citation ranking A link-analysis ranking algorithm that assigns node scores using a random walk mixing normalized outgoing-link transitions with teleportatio…	Curated	Algorithms	`AIMech:PageRank`	6 claims 3 sources
PAIR Passage-Centric Similarity Relation for Dense Passage Retrieval aka PAIR, PAIR Passage-Centric Dense Passage Retrieval… A dense passage retrieval training algorithm that jointly enforces query-centric similarity relations (pulling query q toward positive passa…	Curated	Algorithms	`AIMech:PAIRPassageCentricSimilarityRelationForDenseRetrieval`	4 claims 3 sources
Paired differencing method aka PDM A two-way number-partitioning heuristic that sorts residuals and differences disjoint adjacent pairs in whole rounds, carries an unpaired re…	Curated	Algorithms	`AIMech:PairedDifferencing`	6 claims 2 sources
Pairwise Markov chain aka PMC A hidden-state sequence-model family in which the joint process of a hidden variable and its corresponding observation is first-order Markov…	Curated	Model Families	`AIMech:PairwiseMarkovChain`	1 claim 1 source
Pairwise Markov tree aka Arbre de Markov couple A latent-variable tree-model family whose paired hidden and observed states factor into a root distribution and parent-to-child conditional…	Curated	Model Families	`AIMech:PairwiseMarkovTree`	1 claim 1 source
Papadimitriou 2-SAT random walk A randomized 2-SAT search procedure that starts from any complete truth assignment and repeatedly selects an unsatisfied clause and flips a…	Curated	Algorithms	`AIMech:Papadimitriou2SATRandomWalk`	1 claim 1 source
Parabolic Approximation Line Search aka PAL, PAL Optimizer… A stochastic line-search optimization algorithm for deep neural networks that at each step t defines a one-dimensional loss cross-section l_…	Curated	Algorithms	`AIMech:ParabolicApproximationLineSearch`	4 claims 3 sources
PARADE: Passage Representation Aggregation for Document Reranking aka PARADE Document Reranking Architecture, Passage Representation Aggregation for Document Reranking… A neural document reranking architecture (Li, Yates, MacAvaney, He, & Sun, 2021) that segments a long document D into overlapping passages P…	Curated	Architectures	`AIMech:PARADEPassageRepresentationAggregationForDocumentReranking`	3 claims 3 sources
Parallel alternating Newton-like algorithm for APM A block-alternating Newton-like method for fitting an admixture of Poisson Markov random fields through a sparsity-penalized nodewise Poisso…	Curated	Algorithms	`AIMech:ParallelAlternatingNewtonAPM`	2 claims 3 sources
Parallel Greedy Submodular Maximization in Logarithmic Adaptivity and Nearly-Linear Time via Poly-Logarithmic Batch Filtering aka Ene-Nguyen Nearly-Linear-Time Low-Adaptivity Submodular Maximization, Poly-Logarithmic Batch Filtering for Adaptive Submodular Maximization… Parallel Greedy Submodular Maximization in Logarithmic Adaptivity and Nearly-Linear Time is a randomized parallel value-oracle algorithm int…	Curated	Algorithms	`AIMech:ParallelGreedySubmodularMaximizationInLogarithmicAdaptivityAndNearlyLinearTime`	3 claims 3 sources
Parallel predictive entropy search A batch Bayesian optimization algorithm that jointly selects parallel evaluations of one scalar objective using approximate information gain…	Curated	Algorithms	`AIMech:ParallelPredictiveEntropySearch`	6 claims 2 sources
Parallel predictive entropy search for multi-objective Bayesian optimization with constraints A batch Bayesian optimization algorithm for multiple objectives and unknown constraints that jointly selects parallel evaluation locations u…	Curated	Algorithms	`AIMech:ParallelPredictiveEntropySearchForMultiObjectiveOptimizationWithConstraints`	6 claims 2 sources
Parallel tempering aka Replica exchange Monte Carlo, Metropolis-coupled Markov chain Monte Carlo A population Monte Carlo method that combines within-temperature target-preserving updates with corrected exchanges between replicas targeti…	Curated	Algorithms	`AIMech:ParallelTempering`	1 claim 1 source
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization (BOFT) aka BOFT, Butterfly Orthogonal Fine-Tuning… Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization (BOFT) is a multiplicative parameter-efficient fine-tuning method that…	Curated	Algorithms	`AIMech:BoftOrthogonalButterflyFinetuning`	4 claims 3 sources
Parameter-Expanded Expectation Maximization aka PX-EM, Parameter-Expanded EM An expectation-maximization construction that fits an expanded complete-data model with auxiliary parameters, reduces its result to the orig…	Curated	Algorithms	`AIMech:ParameterExpandedExpectationMaximization`	4 claims 1 source
Parametric UMAP aka Parametric Uniform Manifold Approximation and Projection A parametric dimensionality-reduction algorithm that trains a neural mapping from input points to embedding coordinates using sampled attrac…	Curated	Algorithms	`AIMech:ParametricUMAP`	2 claims 2 sources
ParamILS An iterated-local-search framework for algorithm configuration that searches finite parameter settings through one-parameter neighborhood mo…	Curated	Algorithms	`AIMech:ParamILS`	1 claim 1 source
Partial least squares regression aka PLS regression, PLSR Regression using latent components chosen to capture predictor-response covariance.	Curated	Mathematical Methods	`AIMech:PartialLeastSquaresRegression`	1 claim 1 source
Partially Informed NegaScout A NegaScout variant for adversarial game-tree search that retains prove-best information near the root of each subtree and the principal var…	Curated	Algorithms	`AIMech:PartiallyInformedNegaScout`	4 claims 1 source
Partially noncentered GLMM variational inference A Bayesian generalized linear mixed-model inference procedure that uses cluster-specific partial noncentering to define independent Gaussian…	Curated	Algorithms	`AIMech:PartiallyNoncenteredGLMMVariationalInference`	7 claims 1 source
Partially observable Markov decision process aka POMDP A Markov decision model in which observations provide incomplete information about the current state.	Curated	Model Families	`AIMech:PartiallyObservableMarkovDecisionProcess`	1 claim 1 source
Particle swarm optimization aka PSO A population-based optimization method that moves candidate particles through a search space using retained velocities and stochastic attrac…	Curated	Algorithms	`AIMech:ParticleSwarmOptimization`	3 claims 3 sources
Path integral clustering aka Agglomerative clustering via maximum incremental path integral, PIC (path integral clustering) An agglomerative clustering algorithm that merges clusters with the greatest increase in their size-normalized sums of discounted random-wal…	Curated	Algorithms	`AIMech:PathIntegralClustering`	1 claim 1 source
Patience-controlled FCFS beam decoding aka FCFS beam decoding with controlled patience A generalization of first-come, first-served sequence beam decoding that retains beam width k for continuing hypotheses but uses a positive…	Curated	Algorithms	`AIMech:PatienceControlledBeamDecoding`	2 claims 2 sources
Penalized Focused Generalized Method of Moments (FGMM) for High-Dimensional Endogenous Regression aka Penalized Focused Generalized Method of Moments (FGMM), Fan-Liao High-Dimensional Endogenous FGMM Estimator… A high-dimensional variable-selection and over-identified estimation methodology (introduced by Jianqing Fan and Yuan Liao in 2014) for line…	Curated	Algorithms	`AIMech:PenalizedFocusedGeneralizedMethodOfMomentsForHighDimensionalEndogenousRegression`	3 claims 3 sources
Peng and Williams Q(lambda) The 1996 tabular incremental Q(lambda) algorithm that combines a direct one-step Q-learning update for the current state-action pair with a…	Curated	Algorithms	`AIMech:PengWilliamsQLambda`	6 claims 2 sources
Per-FedAvg Model-Agnostic Meta-Learning for Personalized Federated Learning aka Per-FedAvg, Personalized FedAvg… A personalized federated learning algorithm (Per-FedAvg) grounded in Model-Agnostic Meta-Learning (MAML) that seeks a shared global initiali…	Curated	Algorithms	`AIMech:PerFedAvgModelAgnosticMetaLearningForPersonalizedFederatedLearning`	4 claims 3 sources
Perceptron aka FFN, Feed-Forward Network… An artificial neural network with a supervised learning algorithm for binary classification using a linear predictor function.	AIO	Network	`AIO:Perceptron`	Imported
PERCH clustering aka Purity Enhancing Rotations for Cluster Hierarchies An online hierarchical clustering algorithm that inserts observations near existing leaves of a binary cluster tree and uses masking and bal…	Curated	Algorithms	`AIMech:PERCHClustering`	7 claims 4 sources
PermK Permutation Compressors for Distributed Nonconvex Optimization aka PermK, PermK Permutation Compressor… A family of correlated n-node unbiased random sparsification operators C = (C_1, ..., C_n) (PermK) that jointly generate a random permutatio…	Curated	Algorithms	`AIMech:PermKPermutationCompressorsForDistributedNonconvexOptimization`	4 claims 3 sources
Permute Layer A reshaping layer that permutes the dimensions of the input according to a given pattern.	AIO	Layer	`AIO:PermuteLayer`	Imported
Persistent contrastive divergence aka PCD A learning algorithm that estimates an energy model’s negative-phase statistics with Markov chains whose states persist across parameter upd…	Curated	Algorithms	`AIMech:PersistentContrastiveDivergence`	1 claim 2 sources
Personalized LLM aka Personalized Large Language Model, user adaptation LLM A large language model that adapts its language modeling and generation to the preferences style and persona of individual users or audience…	AIO	Model	`AIO:PersonalizedLLM`	Imported
Perspective Transformer Nets An image-to-volume neural architecture that combines a convolutional image encoder and volumetric decoder with a supplied-camera projection…	Curated	Architectures	`AIMech:PerspectiveTransformerNets`	6 claims 2 sources
Perturbed Accelerated Gradient Descent with Negative-Curvature Reset for Escaping Saddle Points aka Perturbed Accelerated Gradient Descent (PAGD), Jin-Netrapalli-Jordan Accelerated Saddle-Point Escape Algorithm… Perturbed Accelerated Gradient Descent with Negative-Curvature Reset for Escaping Saddle Points (PAGD) is a single-loop, Hessian-free moment…	Curated	Algorithms	`AIMech:PerturbedAcceleratedGradientDescentWithNegativeCurvatureResetForSaddlePointEscape`	3 claims 3 sources
Perturbed Gradient Descent for Escaping Saddle Points in Hessian-Lipschitz Optimization aka Jin-Ge-Netrapalli-Kakade-Jordan Perturbed Gradient Descent (PGD), Hessian-Free Second-Order Stationary Point Convergence via Isotropic Ball Perturbation… Perturbed Gradient Descent for Escaping Saddle Points in Hessian-Lipschitz Optimization is a purely first-order non-convex optimization algo…	Curated	Algorithms	`AIMech:PerturbedGradientDescentForEscapingSaddlePointsInHessianLipschitzOptimization`	3 claims 3 sources
PESC-F An adaptive computation variant of Predictive Entropy Search with Constraints that alternates full inference and acquisition updates with pa…	Curated	Algorithms	`AIMech:PESCF`	6 claims 4 sources
pFedBayes (Personalized Federated Learning via Variational Bayesian Inference) aka pFedBayes, Personalized Federated Variational Bayesian Inference… A personalized federated Bayesian neural network algorithm (Zhang, Li, Li, Guo, & Shao 2022, Section 3, Equations 8-20, Algorithm 1, Theorem…	Curated	Algorithms	`AIMech:PFedBayesPersonalizedFederatedLearningViaVariationalBayesianInference`	4 claims 3 sources
pFedGP (Personalized Federated Learning with Gaussian Processes and Shared Deep Kernel Trees) aka pFedGP, Personalized Federated Learning with Gaussian Processes… A Bayesian personalized federated learning algorithm (Achituve, Shamsian, Navon, Chechik, & Fetaya 2021, Sections 3-4, Equations 1-14, Theor…	Curated	Algorithms	`AIMech:PFedGpPersonalizedFederatedLearningWithGaussianProcessesAndSharedDeepKernelTrees`	4 claims 3 sources
pFedHN (Personalized Federated Hypernetworks) aka pFedHN, Personalized Federated Hypernetworks… A personalized federated learning method (Shamsian, Navon, Fetaya, & Chechik 2021, Section 3, Algorithm 1, Equations 2-4) in which a central…	Curated	Algorithms	`AIMech:PFedHnPersonalizedFederatedHypernetworks`	4 claims 3 sources
pFedLA and HeurpFedLA (Layer-Wised Hypernetwork Model Aggregation for Personalized Federated Learning) aka pFedLA, HeurpFedLA… A layer-wise personalized federated learning framework (Ma, Zhang, Guo, & Xu 2022, Section 3, Equations 1-12, Algorithms 1-2) that deploys a…	Curated	Algorithms	`AIMech:PFedLaAndHeurPFedLaLayerWisedHypernetworkModelAggregationForPersonalizedFederatedLearning`	4 claims 3 sources
pFedMe Personalized Federated Learning with Moreau Envelopes aka pFedMe, Personalized Federated Learning with Moreau Envelopes… A bi-level personalized federated learning algorithm (pFedMe) that formulates global coordination as minimizing the average Moreau envelope…	Curated	Algorithms	`AIMech:PFedMePersonalizedFederatedLearningWithMoreauEnvelopes`	4 claims 3 sources
PhaseLift Convex Semidefinite Programming Matrix-Lifting for Phase Retrieval aka PhaseLift, Convex Semidefinite Relaxation for Phase Retrieval… A convex semidefinite programming (SDP) relaxation and dual-certificate recovery methodology (introduced by Emmanuel J. Candès, Thomas Stroh…	Curated	Algorithms	`AIMech:PhaseLiftConvexSemidefiniteProgrammingPhaseRetrieval`	3 claims 3 sources
PHATE aka Potential of Heat Diffusion for Affinity-based Transition Embedding A dimensionality-reduction algorithm that computes diffusion transition probabilities, measures Euclidean distances between their negative-l…	Curated	Algorithms	`AIMech:PHATE`	1 claim 1 source
Pi-model aka Π-model A semi-supervised classifier-training procedure that combines labeled cross-entropy with squared disagreement between two stochastic predict…	Curated	Algorithms	`AIMech:PiModel`	1 claim 2 sources
Piggyback Binary Weight-Mask Multi-Task Adaptation aka Piggyback, Piggyback Weight Masking… A multi-task and continual neural network adaptation algorithm that freezes all weight matrices W of a pretrained backbone network, associat…	Curated	Algorithms	`AIMech:PiggybackBinaryWeightMaskMultiTaskAdaptation`	4 claims 3 sources
PoClustering edge-clique-cover heuristic An approximate PoClustering algorithm that incrementally extends and prunes clique sets to cover the edges of dissimilarity-threshold graphs…	Curated	Algorithms	`AIMech:PoClusteringEdgeCliqueCover`	6 claims 1 source
PointNet A neural architecture for unordered point clouds that applies shared pointwise feature extraction and symmetric max pooling to produce a glo…	Curated	Architectures	`AIMech:PointNet`	1 claim 1 source
PointNet++ A hierarchical point-set neural architecture that repeatedly samples centroids, groups metric neighborhoods and applies local PointNet featu…	Curated	Architectures	`AIMech:PointNetPlusPlus`	1 claim 1 source
Poisson generalized root model aka Poisson GRM A generalized root probability model on unbounded nonnegative integer counts, with factorial base measures and symmetric products of j-th ro…	Curated	Model Families	`AIMech:PoissonGeneralizedRootModel`	1 claim 1 source
Poisson square root graphical model aka Poisson SQR, Poisson square root Markov random field A square-root graphical model on unbounded nonnegative integer counts with factorial base measures, unary square-root and linear count terms…	Curated	Model Families	`AIMech:PoissonSquareRootGraphicalModel`	1 claim 2 sources
Policy Layer A layer that, after taking a set of states or values as input, predicts a probability distribution of actions to take.	AIO	Layer	`AIO:PolicyLayer`	Imported
Polynomial Codes for Straggler-Resilient High-Dimensional Coded Matrix Multiplication aka Polynomial Codes, (alpha, beta)-Polynomial Code… An algebraic coded distributed computation method proposed by Yu, Maddah-Ali, and Avestimehr (NeurIPS 2017) for computing high-dimensional m…	Curated	Algorithms	`AIMech:PolynomialCodesForStragglerResilientHighDimensionalCodedMatrixMultiplication`	4 claims 3 sources
Polytropon (Latent Task-Skill Allocation for Modular Multitask Learning) aka Polytropon, Skilled Latent-Skill Multitask Model… A modular multitask learning algorithm that assumes each task T_i is associated with a variable-size subset of latent discrete skills from a…	Curated	Algorithms	`AIMech:PolytroponModularSkillAllocation`	4 claims 3 sources
Pooling Layer A layer that serves to mitigate the sensitivity of convolutional layers to location and spatially downsample representations.	AIO	Layer	`AIO:PoolingLayer`	Imported
Popularity Bias A selection and sampling bias where more popular items are more exposed under-representing less popular items.	AIO	Bias	`AIO:PopularityBias`	Imported
Population Based Augmentation aka PBA An augmentation-schedule learning procedure that jointly trains a population of child classifiers and evolves their augmentation hyperparame…	Curated	Algorithms	`AIMech:PopulationBasedAugmentation`	2 claims 3 sources
Population Based Training aka PBT A population-based neural-network training procedure that interleaves parameter updates with performance-guided copying of partially trained…	Curated	Algorithms	`AIMech:PopulationBasedTraining`	1 claim 1 source
Population Bias A selection and sampling bias characterized by systematic distortions in demographics or other user characteristics between represented user…	AIO	Bias	`AIO:PopulationBias`	Imported
Population-based incremental learning aka PBIL An optimization method that samples candidate solutions from a probability-vector representation and incrementally moves that representation…	Curated	Algorithms	`AIMech:PopulationBasedIncrementalLearning`	1 claim 1 source
Population-to-Sample Contraction, First-Order Stability (FOS), and Gradient Stability (GS) Framework for the EM Algorithm aka Balakrishnan-Wainwright-Yu Population-to-Sample EM Framework, First-Order Stability (FOS) and Gradient Stability (GS) EM Contraction Analysis… A two-stage population-to-sample non-asymptotic analytical framework (introduced by Sivaraman Balakrishnan, Martin J. Wainwright, and Bin Yu…	Curated	Mathematical Methods	`AIMech:PopulationToSampleContractionAndFirstOrderStabilityEM`	4 claims 3 sources
Post-Local Stochastic Gradient Descent aka Post-Local SGD, Two-Phase Post-Local SGD… A two-phase distributed stochastic gradient optimization algorithm across K parallel workers with local mini-batch size B_loc that sets the…	Curated	Algorithms	`AIMech:PostLocalSgdTwoPhaseDistributedOptimization`	4 claims 3 sources
Post-model-selection predictor PoSI confidence intervals under full and active-only covariate observation aka Bachoc-Leeb-Pötscher post-model-selection predictor confidence intervals, Active-covariate partial-union-bound predictor PoSI hierarchy (K_1, K_2, K_3, K_4, K_5)… A post-model-selection inference methodology for linear regression predictors x_0'[M_hat] beta_hat_{M_hat} +- K(x_0, M_hat) * \|\|s_{M_hat}\|\|…	Curated	Mathematical Methods	`AIMech:PostModelSelectionPredictorPoSIConfidenceIntervals`	4 claims 3 sources
Power iteration clustering aka PIC (power iteration clustering) A clustering algorithm that uses an early-stopped power iteration of a normalized similarity matrix to embed observations and then applies k…	Curated	Algorithms	`AIMech:PowerIterationClustering`	2 claims 2 sources
Power-of-Choice (Biased Loss-Based Client Selection Strategies for Federated Learning: pow-d, cpow-d, and rpow-d) aka Power-of-Choice Client Selection, pow-d, cpow-d, and rpow-d Federated Client Selection… A biased client-selection framework and theoretical convergence analysis for partial-participation federated learning (Cho, Wang, & Joshi 20…	Curated	Algorithms	`AIMech:PowerOfChoiceBiasedLossClientSelectionForFederatedLearning`	4 claims 3 sources
PowerGossip Low-Rank Communication Compression for Decentralized Deep Learning aka PowerGossip, PowerGossip Low-Rank Compressed Decentralized SGD… A hyperparameter-free compressed gossip and decentralized stochastic optimization algorithm (PowerGossip) that directly compresses pairwise…	Curated	Algorithms	`AIMech:PowerGossipLowRankCommunicationCompressionForDecentralizedDeepLearning`	4 claims 3 sources
PowerSGD Low-Rank Subspace Iteration Gradient Compression with Error Feedback aka PowerSGD, Low-Rank Gradient Compression via Subspace Iteration… A distributed low-rank gradient compression algorithm (PowerSGD) that reshapes each parameter tensor's error-compensated gradient matrix Del…	Curated	Algorithms	`AIMech:PowerSgdLowRankGradientCompressionWithErrorFeedback`	4 claims 3 sources
PPT Pre-Trained Prompt Tuning for Few-Shot Learning aka PPT, Pre-trained Prompt Tuning… A parameter-efficient few-shot prompt-tuning framework that groups downstream classification tasks into format-specific or unified multiple-…	Curated	Algorithms	`AIMech:PPTPretrainedPromptTuningForFewShotLearning`	4 claims 3 sources
Preconditioned Crank–Nicolson Langevin sampling aka pCNL A Metropolis-corrected Gaussian-reference sampler that preconditions the potential-gradient drift by the reference covariance and uses a sca…	Curated	Algorithms	`AIMech:PreconditionedCrankNicolsonLangevin`	1 claim 1 source
Preconditioned Crank–Nicolson sampling aka pCN A Metropolis sampler for a Gaussian-reference target whose proposal combines the current state with an independent draw from that reference…	Curated	Algorithms	`AIMech:PreconditionedCrankNicolson`	1 claim 1 source
Predictive Entropy Search A Bayesian global optimization algorithm that approximates information about the global maximizer by subtracting maximizer-conditioned predi…	Curated	Algorithms	`AIMech:PredictiveEntropySearch`	6 claims 3 sources
Predictive entropy search for multi-objective Bayesian optimization A Bayesian multi-objective optimization algorithm that selects evaluations using an approximate information gain about the Pareto set, compu…	Curated	Algorithms	`AIMech:PredictiveEntropySearchForMultiObjectiveOptimization`	6 claims 3 sources
Predictive entropy search for multi-objective Bayesian optimization with constraints A Bayesian optimization algorithm for multiple objectives and unknown constraints that selects evaluations using approximate information gai…	Curated	Algorithms	`AIMech:PredictiveEntropySearchForMultiObjectiveOptimizationWithConstraints`	6 claims 4 sources
Predictive Entropy Search with Constraints A Bayesian optimization algorithm for an unknown objective and unknown inequality constraints that selects evaluations using an approximatio…	Curated	Algorithms	`AIMech:PredictiveEntropySearchWithConstraints`	6 claims 3 sources
PReLU Layer An activation layer that applies parametric rectified linear unit function element-wise.	AIO	Layer	`AIO:PReLULayer`	Imported
Preprocessing A process applied to raw data before it is used in a machine learning model, including tasks such as normalization, scaling, encoding, and t…	AIO	Preprocessing	`AIO:Preprocessing`	Imported
Preprocessing Layer A layer that performs data preprocessing operations.	AIO	Layer	`AIO:PreprocessingLayer`	Imported
Presentation Bias An individual bias arising from how information is presented on the Web via a user interface due to rating or ranking of output or through u…	AIO	Bias	`AIO:PresentationBias`	Imported
PreTTR Precomputing Transformer Term Representations aka PreTTR, Precomputing Transformer Term Representations… A decoupled-layer Transformer document re-ranking architecture and token-representation compression method that applies a cross-segment atte…	Curated	Architectures	`AIMech:PreTTRPrecomputingTermRepresentationsForReranking`	4 claims 3 sources
Primal-Dual Witness Method and Sharp Thresholds for High-Dimensional Noisy Lasso Sparsity Recovery aka Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using l_1-Constrained Quadratic Programming (Wainwright 2009), Wainwright Primal-Dual Witness Method for Exact Signed Support Recovery of the Lasso… Primal-Dual Witness Method and Sharp Thresholds for High-Dimensional Noisy Lasso Sparsity Recovery is a convex-optimality and high-dimension…	Curated	Mathematical Methods	`AIMech:PrimalDualWitnessAndSharpThresholdsForHighDimensionalNoisyLassoSparsityRecovery`	3 claims 3 sources
Principal Component Analysis aka PCA A dimensionality reduction method for analyzing large datasets with high-dimensional features per observation increasing data interpretabili…	AIO	MachineLearningTask	`AIO:PrincipalComponentAnalysis`	Imported
Principal Curves aka Hastie–Stuetzle Principal Curves A nonlinear statistical summary defined by a smooth curve that is self-consistent for a data distribution: almost every point on the curve e…	Curated	Mathematical Methods	`AIMech:PrincipalCurves`	4 claims 1 source
Principal Orthogonal Complement Thresholding (POET) for High-Dimensional Approximate Factor Covariance Estimation aka POET Covariance Estimator, Principal Orthogonal Complement Thresholding… A nonparametric high-dimensional covariance and precision matrix estimation methodology (introduced by Jianqing Fan, Yuan Liao, and Martina…	Curated	Algorithms	`AIMech:PrincipalOrthogonalComplementThresholdingForApproximateFactorCovarianceEstimation`	3 claims 3 sources
Principal Singular Values and Singular Vectors Adaptation (PiSSA) aka PiSSA, Principal Singular Values and Singular Vectors Adaptation… Principal Singular Values and Singular Vectors Adaptation (PiSSA) is a parameter-efficient fine-tuning (PEFT) method that shares the exact a…	Curated	Algorithms	`AIMech:PissaPrincipalSingularValuesAndSingularVectorsAdaptation`	4 claims 3 sources
Prior-Expansion Marginal Likelihood Score Prior-Data Conflict Check aka Prior-Expansion Score Conflict Check, Marginal Likelihood Score Prior-Data Conflict Diagnostic… A Bayesian model criticism and prior-data conflict evaluation method that embeds a working prior p_0(theta) into a continuous expansion fami…	Curated	Evaluation Methods	`AIMech:PriorExpansionMarginalLikelihoodScorePriorDataConflictCheck`	4 claims 3 sources
Prior-expansion score conflict diagnostic A Bayesian prior-data conflict diagnostic that embeds a baseline prior density g(theta) into a smoothly parameterized expansion family g(the…	Curated	Algorithms	`AIMech:PriorExpansionScoreConflictDiagnostic`	7 claims 2 sources
Prior-to-posterior divergence conflict diagnostic aka Prior-to-posterior Rényi divergence prior-data conflict check, Relative belief prior-to-posterior divergence conflict diagnostic A Bayesian prior-data conflict diagnostic algorithm that measures belief change from a proper prior g(theta) to the posterior g(theta \| y) u…	Curated	Algorithms	`AIMech:PriorToPosteriorDivergenceConflictDiagnostic`	4 claims 2 sources
Probabilistic Graphical Model aka Graphical Model, PGM… A machine learning task in which a graph expresses the conditional dependence structure between random variables.	AIO	MachineLearningTask	`AIO:ProbabilisticGraphicalModel`	Imported
Probabilistic Hidden Layer A hidden layer that estimates the probability of a sample being within a certain category.	AIO	Layer	`AIO:ProbabilisticHiddenLayer`	Imported
Probabilistic latent semantic analysis aka PLSA, Probabilistic latent semantic indexing… A latent-class model of document–word or other dyadic co-occurrences that represents their joint probability as a mixture of conditionally i…	Curated	Model Families	`AIMech:ProbabilisticLatentSemanticAnalysis`	1 claim 2 sources
Probabilistic Principal Component Analysis aka PPCA A linear Gaussian latent-variable model with a standard-normal latent prior and isotropic observation noise, whose maximum-likelihood loadin…	Curated	Model Families	`AIMech:ProbabilisticPCA`	4 claims 1 source
Probabilistic Topic Model A probabilistic graphical model that uses statistical techniques to analyze the words in each text to discover common themes their connectio…	AIO	MachineLearningTask	`AIO:ProbabilisticTopicModel`	Imported
Probability of improvement acquisition An acquisition criterion for scalar optimization that scores a candidate by the predictive probability of meeting a specified improvement th…	Curated	Mathematical Methods	`AIMech:ProbabilityOfImprovementAcquisition`	6 claims 2 sources
Processing Bias aka Validation Bias A computational bias resulting from judgment modulated by affect influenced by the level of efficacy and efficiency in information processin…	AIO	Bias	`AIO:ProcessingBias`	Imported
Procrustean Matrix Decomposition and Two-to-Infinity Norm Singular Subspace Perturbation Bounds aka Two-to-Infinity Norm Singular Subspace Perturbation Bound, Cape-Tang-Priebe Procrustean Matrix Decomposition… A deterministic and probabilistic row-wise singular subspace perturbation framework (introduced by Joshua Cape, Minh Tang, and Carey E. Prie…	Curated	Mathematical Methods	`AIMech:ProcrusteanMatrixDecompositionAndTwoToInfinityNormSingularSubspacePerturbationBounds`	3 claims 3 sources
Procrustes Flow (Factored Gradient Descent with $U^\top U = V^\top V$ Balancing Regularization) for Low-Rank Matrix Recovery aka Procrustes Flow (PF) for Low-Rank Matrix Sensing, Factored Gradient Descent with Factor-Balancing Regularizer \|\|U^T U - V^T V\|\|_F^2… A two-stage non-convex Burer-Monteiro factored optimization algorithm and geometric convergence analysis (introduced by Stephen Tu, Ross Boc…	Curated	Algorithms	`AIMech:ProcrustesFlowForLowRankMatrixRecovery`	4 claims 3 sources
Prodigy (Expeditiously Adaptive Parameter-Free Optimization) aka Prodigy Optimizer, Prodigy Parameter-Free Learner… A parameter-free adaptive optimization algorithm that estimates the initial distance to the solution D = \|\|x_0 - x_*\|\| online via a monotoni…	Curated	Algorithms	`AIMech:ProdigyExpeditiouslyAdaptiveParameterFreeOptimization`	4 claims 3 sources
Product of experts aka PoE, Products of experts A probabilistic model family that combines expert factors over the same observations by multiplying their values and normalizing the product…	Curated	Model Families	`AIMech:ProductOfExperts`	1 claim 2 sources
Product of hidden Markov models aka PoHMM, Products of hidden Markov models A sequence-model family that multiplies the marginal probabilities assigned to a complete observation sequence by several hidden Markov mode…	Curated	Model Families	`AIMech:ProductOfHiddenMarkovModels`	1 claim 2 sources
Product of Student-t aka Product of Student-t Model, PoT A normalized energy-based density on continuous observations formed from products of Student-t-shaped factors of linear filter responses, wi…	Curated	Model Families	`AIMech:ProductOfStudentT`	4 claims 1 source
Professor forcing An adversarial recurrent-network training procedure that retains teacher-forced likelihood learning while training an auxiliary discriminato…	Curated	Algorithms	`AIMech:ProfessorForcing`	6 claims 1 source
Projected Attention Layers aka PALs, BERT and PALs… A task-specific parallel multi-head attention adaptation layer for multi-task Transformer models that transforms each layer's hidden states…	Curated	Layers & Modules	`AIMech:PALsProjectedAttentionLayers`	4 claims 3 sources
Projected Hotelling T-squared divide-and-combine confidence region aka Half-Cauchy Divide-and-Combine Multivariate Confidence Region, Projected Hotelling's T^2 Half-Cauchy Confidence Region… A multivariate statistical inference and meta-analysis method (Liu, Meng, & Pillai 2025) that constructs a guaranteed convex, bounded joint…	Curated	Mathematical Methods	`AIMech:ProjectedHotellingT2DivideAndCombineConfidenceRegion`	4 claims 2 sources
Projected Power Method for Joint Alignment from Pairwise Modulo Differences aka Projected Power Method (PPM) for Joint Alignment, Chen-Candes Projected Power Iteration for Cyclic Group Synchronization… A nonconvex iterative discrete synchronization and joint alignment algorithm (introduced by Yuxin Chen and Emmanuel J. Candès in 2018) for r…	Curated	Algorithms	`AIMech:ProjectedPowerMethodForJointAlignmentFromPairwiseModuloDifferences`	3 claims 3 sources
Projection-Cost Preserving Sketches for k-Means Clustering and Constrained Low-Rank Approximation aka Projection-Cost Preserving Sketch (PCPS), Rank-k Projection-Cost Preserving Dimensionality Reduction… A Rank-k Projection-Cost Preserving Sketch (PCPS) is a linear dimensionality-reduction sketch A_tilde in R^{n x d'} (with d' << d) of a data…	Curated	Preprocessing Methods	`AIMech:ProjectionCostPreservingSketchesForKMeansAndConstrainedLowRankApproximation`	3 claims 3 sources
PRoLoRA aka Partially Rotation-Enhanced Low-Rank Adaptation, Partial Rotation Intra-Layer Shared LoRA… A parameter-efficient low-rank adaptation architecture that combines intra-layer hidden-dimension chunk broadcasting with rank-dimension cir…	Curated	Architectures	`AIMech:PRoLoRA`	4 claims 3 sources
Prompt-based Fine-Tuning LLM aka Prompt-based Fine-Tuning Large Language Model, Prompt-tuned Large Language Model… A large language model which is fine-tuned on a small number of examples or prompts, rather than full task datasets. This allows for rapid a…	AIO	Model	`AIO:PromptbasedFineTuningLLM`	Imported
Promptagator Few-Shot Dense Retrieval aka Promptagator, Prompt-based Query Generation for Retriever… A few-shot dense retrieval training method (Prompt-based Query Generation for Retriever) that prompts a large language model with task-speci…	Curated	Algorithms	`AIMech:PromptagatorFewShotDenseRetrievalDataGeneration`	4 claims 3 sources
PromptFL: Federated Continuous Prompt Learning for Foundation Models aka PromptFL, Federated Prompt Training for Foundation Models… A parameter-efficient federated foundation-model adaptation framework (PromptFL; Guo, Guo, Wang, Tang, and Xu, IEEE Transactions on Mobile C…	Curated	Algorithms	`AIMech:PromptFlFederatedPromptLearningForFoundationModels`	4 claims 3 sources
PROP Pre-Training with Representative Words Prediction for Ad-Hoc Retrieval aka PROP, Pre-training with Representative Words Prediction… A self-supervised pre-training algorithm tailored for ad-hoc document retrieval that estimates a Dirichlet-prior-smoothed multinomial unigra…	Curated	Algorithms	`AIMech:PROPPreTrainingWithRepresentativeWordsPrediction`	4 claims 3 sources
Proportional Hazards Model A regression analysis for survival analysis where the unique effect of a unit increase in a covariate is multiplicative with respect to the…	AIO	MachineLearningTask	`AIO:ProportionalHazardsModel`	Imported
Prototype-based domain description aka PDD radius-offset rule A one-class decision rule that accepts a query when its metric distance to at least one prototype, plus that prototype's stored radius offse…	Curated	Algorithms	`AIMech:PrototypeBasedDomainDescription`	4 claims 1 source
Prototypical Calibration for Few-Shot Language Models aka PROCA, Prototypical Calibration… A decision-boundary calibration algorithm for zero- and few-shot language model classification (PROCA) that models the N-dimensional log-pro…	Curated	Algorithms	`AIMech:PrototypicalCalibrationForFewShotLanguageModels`	4 claims 3 sources
Proximal policy optimization aka PPO A family of policy-gradient algorithms alternating collected interaction data with repeated optimization of a surrogate objective using clip…	Curated	Algorithms	`AIMech:ProximalPolicyOptimization`	1 claim 1 source
ProxSkip and Scaffnew Probabilistic Proximal Skipping for Accelerated Local Gradient Descent aka ProxSkip, Scaffnew… A randomized composite first-order optimization algorithm (ProxSkip) and its federated consensus instantiation (Scaffnew) for minimizing f(x…	Curated	Algorithms	`AIMech:ProxSkipAndScaffnewProbabilisticProximalSkippingForAcceleratedLocalGradientDescent`	4 claims 3 sources
ProxSkip-VR and ProxSkip-HUB Variance-Reduced Local Training and Regional-Hub Federated Optimization aka ProxSkip-VR, ProxSkip-HUB… A general variance-reduced randomized proximal-skipping framework (ProxSkip-VR) and hierarchical server-hubs-clients federated optimization…	Curated	Algorithms	`AIMech:ProxSkipVrAndProxSkipHubVarianceReducedLocalTrainingAndRegionalHubFederatedOptimization`	4 claims 3 sources
PruneFL: Adaptive and Distributed Parameter Pruning for Federated Learning aka PruneFL, Adaptive and Distributed Parameter Pruning for Federated Learning An adaptive distributed parameter pruning and reconfiguration framework for federated learning (PruneFL; Jiang, Wang, Valls, Ko, Lee, Leung,…	Curated	Algorithms	`AIMech:PruneFlAdaptiveDistributedParameterPruningForFederatedLearning`	4 claims 3 sources
Pseudo-Label A semi-supervised neural-network training procedure that recomputes hard labels from the model’s most probable class for unlabeled examples…	Curated	Algorithms	`AIMech:PseudoLabel`	2 claims 1 source
Pseudo-linear regression estimation aka Pseudo-linear regression algorithm A family of recursive coefficient estimators that uses the current regressor as a surrogate prediction sensitivity, omitting derivatives thr…	Curated	Algorithms	`AIMech:PseudoLinearRegressionEstimation`	5 claims 1 source
PTR Prompt Tuning with Rules aka PTR, Prompt Tuning with Rules… A prompt-tuning method for many-class text and relation classification that decomposes each target class y in Y into a conjunctive normal fo…	Curated	Algorithms	`AIMech:PTRPromptTuningWithRules`	4 claims 3 sources
Push-Pull and G-Push-Pull Gradient Methods for Distributed Optimization aka Push-Pull and G-Push-Pull, Push-Pull Distributed Gradient Method… A directed-graph distributed gradient tracking method and its asynchronous gossip extension (Pu, Shi, Xu, & Nedic 2021, Section II, Algorith…	Curated	Algorithms	`AIMech:PushPullAndGPushPullGradientMethodsForDistributedOptimization`	4 claims 3 sources
Q-BERT: Hessian-Based Ultra Low Precision Quantization of BERT aka Q-BERT, Q-BERT Hessian Mixed-Precision Quantization… An ultra-low-bit quantization-aware compression algorithm for Transformer language models that computes layer-wise top Hessian eigenvalue di…	Curated	Algorithms	`AIMech:QBERTHessianBasedUltraLowPrecisionQuantizationOfBERT`	4 claims 3 sources
q-Fair Federated Learning (q-FFL) and q-FedAvg for Alpha-Fair Resource Allocation aka q-FFL, q-Fair Federated Learning… A fairness-aware federated optimization formulation (q-Fair Federated Learning, q-FFL) and its communication-efficient solver (q-FedAvg) ins…	Curated	Algorithms	`AIMech:QFairFederatedLearningAlphaFairResourceAllocation`	4 claims 3 sources
Q-GaLore (Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients) aka Q-GaLore, Quantized GaLore… A memory-efficient quantized low-rank gradient-projection optimization algorithm for pre-training and fine-tuning large language models that…	Curated	Algorithms	`AIMech:QGaLoreQuantizedLowRankGradientProjection`	5 claims 3 sources
Q-learning A model-free reinforcement-learning method that incrementally updates action-value estimates toward an observed reward plus the discounted m…	Curated	Algorithms	`AIMech:QLearning`	1 claim 1 source
Q-routing A distributed adaptive packet-routing algorithm that learns destination-specific delivery-time estimates by combining observed local queue a…	Curated	Algorithms	`AIMech:QRouting`	1 claim 1 source
QDS-Transformer: Query-Directed Sparse Transformer for Long Document Ranking aka Query-Directed Sparse Transformer, QDS-Transformer Long Document Ranker… A long-document ranking Transformer architecture (Jiang, Xiong, Lee, & Wang, Findings of EMNLP 2020) that replaces the dense n x n self-atte…	Curated	Architectures	`AIMech:QDSTransformerQueryDirectedSparseTransformerForLongDocumentRanking`	3 claims 3 sources
QSGD (Quantized Stochastic Gradient Descent) with Elias Coding aka QSGD, Quantized SGD… A communication-efficient family of unbiased stochastic gradient quantization and lossless prefix-coding schemes (Alistarh, Grubic, Li, Tomi…	Curated	Algorithms	`AIMech:QsgdQuantizedStochasticGradientDescentWithEliasCoding`	3 claims 3 sources
Qsparse-local-SGD (Distributed SGD with Quantization, Sparsification, and Local Computations) aka Qsparse-local-SGD, Quantized Sparsified Local Stochastic Gradient Descent… A unified distributed and decentralized optimization algorithm (Basu et al. 2019, Algorithms 1-2) that combines local multi-step SGD updates…	Curated	Algorithms	`AIMech:QsparseLocalSgdQuantizationSparsificationAndLocalComputation`	4 claims 3 sources
Quadratic discriminant analysis aka QDA Gaussian discriminant classification with class-specific covariance matrices.	Curated	Model Families	`AIMech:QuadraticDiscriminantAnalysis`	1 claim 1 source
Quadratic Poisson graphical model aka QPGM, Quadratic Poisson Markov random field A graphical probability model on nonnegative integer counts whose joint log mass contains unary linear terms, site quadratic terms and symme…	Curated	Model Families	`AIMech:QuadraticPoissonGraphicalModel`	1 claim 2 sources
Quant-Noise (Training with Quantization Noise for Extreme Model Compression) aka Quant-Noise, Training with Quantization Noise for Extreme Model Compression… Quant-Noise is a quantization-aware neural network training method that partitions each weight matrix W in R^{n x p} into m x q subvector bl…	Curated	Algorithms	`AIMech:QuantNoiseTrainingWithQuantizationNoiseForExtremeCompression`	4 claims 3 sources
Quantization-Aware Low-Rank Adaptation (QA-LoRA) aka QA-LoRA, Quantization-Aware Low-Rank Adaptation… Quantization-Aware Low-Rank Adaptation (QA-LoRA) is a joint low-bit quantization and parameter-efficient fine-tuning algorithm for large lan…	Curated	Algorithms	`AIMech:QaloraQuantizationAwareLowRankAdaptation`	4 claims 3 sources
Quasi-Global Momentum for Heterogeneous Decentralized Deep Learning aka Quasi-Global Momentum, QG-DSGDm… A communication-free momentum acceleration mechanism for decentralized stochastic optimization (QG-DSGDm / QG-DSGDm-N / QG-DAdam) that repla…	Curated	Algorithms	`AIMech:QuasiGlobalMomentumForHeterogeneousDecentralizedDeepLearning`	4 claims 3 sources
Quasi-Hyperbolic Momentum (QHM) and Quasi-Hyperbolic Adam (QHAdam) Optimization aka QHM, QHAdam… Quasi-Hyperbolic Momentum (QHM) and Quasi-Hyperbolic Adam (QHAdam) are first-order stochastic optimization algorithms (Ma & Yarats, ICLR 201…	Curated	Algorithms	`AIMech:QhmAndQhAdamQuasiHyperbolicMomentumAndAdaptiveOptimization`	4 claims 3 sources
R-Novelty SAT heuristic aka R-Novelty A Novelty-derived SAT heuristic whose choice between the best and second-best flips depends on their objective-score gap when the best varia…	Curated	Algorithms	`AIMech:RNovelty`	2 claims 3 sources
R-Novelty+ SAT heuristic aka R-Novelty+ The 1999 R-Novelty extension that replaces its periodic random override with a fixed per-step probability of a random clause-variable flip a…	Curated	Algorithms	`AIMech:RNoveltyPlus`	3 claims 3 sources
Radial Basis Network aka RBFN, RBN… A deep feedforward network that uses radial basis functions as activation functions for pattern recognition and interpolation.	AIO	Network	`AIO:RadialBasisNetwork`	Imported
Radicchi edge-clustering community detection aka Radicchi divisive algorithm, modified edge-clustering community detection A divisive graph-community algorithm family that repeatedly removes edges with the lowest modified cycle-based edge-clustering score, update…	Curated	Algorithms	`AIMech:RadicchiEdgeClustering`	7 claims 1 source
RAM Random Accelerated Motion Multidimensional Time Series Generator aka RAM Time Series Generator, Random Accelerated Motion Time Series Generator… A synthetic multidimensional time series generation algorithm that models a D-dimensional time series as the trajectory of a point mass unde…	Curated	Algorithms	`AIMech:RAMRandomAcceleratedMotionMultidimensionalTimeSeriesGenerator`	4 claims 3 sources
RandAugment An image-augmentation procedure that applies a uniformly sampled sequence of operations sharing one magnitude parameter, reducing augmentati…	Curated	Algorithms	`AIMech:RandAugment`	1 claim 1 source
RandGreeDi and NMRandGreeDi Randomized Distributed Submodular Maximization under Hereditary Constraints aka RandGreeDi Algorithm, NMRandGreeDi Non-Monotone Randomized Distributed Greedy Algorithm… RandGreeDi and NMRandGreeDi are two-round randomized distributed MapReduce algorithms introduced by Barbosa, Ene, Nguyen, and Ward (2015) fo…	Curated	Algorithms	`AIMech:RandGreeDiRandomizedDistributedSubmodularMaximization`	3 claims 3 sources
Random Effects Model aka REM A regression analysis where the model parameters are random variables.	AIO	MachineLearningTask	`AIO:RandomEffectsModel`	Imported
Random Forest An ensemble learning method for classification regression and other tasks that constructs a multitude of decision trees during training.	AIO	MachineLearningTask	`AIO:RandomForest`	Imported
Random Online Aggressive Racing aka ROAR, Random Online Adaptive Racing An algorithm-configuration procedure that proposes uniformly random parameter settings and compares each challenger with an incumbent throug…	Curated	Algorithms	`AIMech:RandomOnlineAggressiveRacing`	1 claim 1 source
Random Search for Hyperparameter Optimization aka Random Hyperparameter Search A hyperparameter optimization procedure that draws trial configurations independently from a specified search distribution, evaluates their…	Curated	Algorithms	`AIMech:RandomSearchHyperparameterOptimization`	1 claim 1 source
Random-only abstraction for abstraction sampling aka Random-only abstraction sampling, simpleRand abstraction… A randomized abstraction rule for graphical-model sampling that uniformly permutes the current search nodes and divides that order into grou…	Curated	Mathematical Methods	`AIMech:RandomOnlyAbstractionSampling`	6 claims 1 source
Random-walk Metropolis–Hastings sampling aka RWMH A Metropolis–Hastings sampler that proposes a new state by adding an increment drawn from a fixed distribution independent of the current st…	Curated	Algorithms	`AIMech:RandomWalkMetropolisHastings`	1 claim 1 source
RandomBrightness Layer An image preprocessing layer that randomly adjusts brightness during training.	AIO	Layer	`AIO:RandomBrightnessLayer`	Imported
RandomContrast Layer An image preprocessing layer that randomly adjusts contrast during training.	AIO	Layer	`AIO:RandomContrastLayer`	Imported
RandomCrop Layer An image preprocessing layer that randomly crops images during training.	AIO	Layer	`AIO:RandomCropLayer`	Imported
RandomFlip Layer An image preprocessing layer that randomly flips images during training.	AIO	Layer	`AIO:RandomFlipLayer`	Imported
RandomHeight Layer An image preprocessing layer that randomly varies image height during training.	AIO	Layer	`AIO:RandomHeightLayer`	Imported
Randomized Block Krylov Iteration for Gap-Independent Approximate SVD and Principal Component Analysis aka Musco-Musco Randomized Block Krylov Iteration, Gap-Independent Randomized Block Lanczos SVD… Randomized Block Krylov Iteration for Gap-Independent Approximate SVD and Principal Component Analysis is a randomized matrix-decomposition…	Curated	Algorithms	`AIMech:RandomizedBlockKrylovMethodsForApproximateSingularValueDecomposition`	3 claims 3 sources
Randomized Kaczmarz Algorithm with Exponential Convergence aka Strohmer-Vershynin Randomized Kaczmarz Algorithm, Row-Norm Weighted Randomized Kaczmarz Method… Randomized Kaczmarz Algorithm with Exponential Convergence is a stochastic row-action iterative solver introduced by Strohmer and Vershynin…	Curated	Algorithms	`AIMech:RandomizedKaczmarzAlgorithmWithExponentialConvergence`	3 claims 3 sources
Randomized latent score conflict diagnostic aka Randomised latent score conflict diagnostic A Bayesian hierarchical-model diagnostic that freezes draws from a parent posterior excluding selected child data, draws child latent parame…	Curated	Algorithms	`AIMech:RandomizedLatentScoreConflictDiagnostic`	8 claims 1 source
Randomized Sketches of Convex Programs with Tangent-Cone Gaussian-Width Cost-Approximation and Privacy Mutual-Information Guarantees aka Randomized Sketches of Convex Programs with Sharp Guarantees (Pilanci & Wainwright 2015), Tangent-Cone Gaussian-Width Sketched Convex Programming… Randomized Sketches of Convex Programs with Tangent-Cone Gaussian-Width Cost-Approximation and Privacy Mutual-Information Guarantees is a co…	Curated	Mathematical Methods	`AIMech:RandomizedSketchesOfConvexProgramsWithTangentConeGaussianWidthGuarantees`	3 claims 3 sources
Randomly Initialized Gradient Descent and Leave-One-Out Sign-Flip Phase Retrieval Analysis aka Randomly Initialized Wirtinger Flow Global Convergence Analysis, Chen-Chi-Fan-Ma Two-Stage Phase Retrieval Trajectory Analysis… The global convergence theory and two-stage trajectory analysis of vanilla Wirtinger Flow gradient descent $x^{t+1} = x^t - \eta_t \nabla f(…	Curated	Algorithms	`AIMech:RandomlyInitializedGradientDescentAndLeaveOneOutSignFlipPhaseRetrievalAnalysis`	4 claims 3 sources
RandomRotation Layer An image preprocessing layer that randomly rotates images during training.	AIO	Layer	`AIO:RandomRotationLayer`	Imported
RandomTranslation Layer An image preprocessing layer that randomly translates images during training.	AIO	Layer	`AIO:RandomTranslationLayer`	Imported
RandomWidth Layer An image preprocessing layer that randomly varies image width during training.	AIO	Layer	`AIO:RandomWidthLayer`	Imported
RandomZoom Layer An image preprocessing layer that randomly zooms in or out on images during training.	AIO	Layer	`AIO:RandomZoomLayer`	Imported
RandProx (Primal-Dual Optimization with Randomized Proximal Updates) aka RandProx, Randomized Primal-Dual Proximal Splitting… A variance-reduced randomized primal-dual proximal splitting algorithm (Condat & Richtarik 2023, Sections 2-3, Equations 4-11, Algorithm 1)…	Curated	Algorithms	`AIMech:RandProxPrimalDualOptimizationWithRandomizedProximalUpdates`	4 claims 3 sources
Rank Centrality Iterative Random-Walk Spectral Ranking from Pairwise Comparisons aka Rank Centrality Algorithm, Negahban-Oh-Shah Spectral Ranking from Pairwise Comparisons… An iterative spectral rank-aggregation algorithm (introduced by Sahand Negahban, Sewoong Oh, and Devavrat Shah in 2017) that estimates laten…	Curated	Algorithms	`AIMech:RankCentralityIterativeRandomWalkSpectralRankingFromPairwiseComparisons`	3 claims 3 sources
Rank-based Ant System aka ASrank An Ant System variant that weights pheromone deposits from a selected number of the current iteration’s best tours by rank and adds a separa…	Curated	Algorithms	`AIMech:RankBasedAntSystem`	1 claim 1 source
Ranking Bias An anchoring bias characterized by the idea that top-ranked results are the most relevant and important leading to more clicks than other re…	AIO	Bias	`AIO:RankingBias`	Imported
RAPID support vector data description sampling aka RAPID, Reducing samples by pruning of inlier densities A density-based training-subset selection method for support vector data description that prefilters low-density observations and greedily r…	Curated	Preprocessing Methods	`AIMech:RapidSupportVectorDataDescriptionSampling`	8 claims 5 sources
Rashomon Effect Bias aka Rashomon Effect, Rashomon Principle An individual bias characterized by differences in perspective memory recall interpretation and reporting of the same event by multiple pers…	AIO	Bias	`AIO:RashomonEffectBias`	Imported
Rate-adapting Poisson model aka RAP A harmonium model family coupling unbounded visible Poisson counts to finite binomial hidden variables through bilinear interactions that sh…	Curated	Model Families	`AIMech:RateAdaptingPoissonModel`	3 claims 1 source
RBFS-epsilon aka RBFSϵ A recursive best-first search variant that adds a finite nonnegative epsilon tolerance to the competitive expansion threshold, retaining the…	Curated	Algorithms	`AIMech:RBFSEpsilon`	4 claims 1 source
RBFS-kth-root aka RBFSkthrt A bounded-suboptimal recursive best-first search variant that divides a quality budget w between a heuristic factor w^((k-1)/k) and a compet…	Curated	Algorithms	`AIMech:RBFSKthRoot`	4 claims 1 source
Real-time A* aka RTA*, Real-time A-star A real-time heuristic search algorithm that moves to a neighbor with minimum edge-cost-plus-heuristic estimate and stores the second-best su…	Curated	Algorithms	`AIMech:RealTimeAStar`	1 claim 2 sources
Real-Time Adaptive A* aka RTAA* A real-time heuristic search algorithm that repeatedly runs bounded forward A*, updates every expanded state to the selected next-to-expand…	Curated	Algorithms	`AIMech:RealTimeAdaptiveAStar`	8 claims 2 sources
Real-time recurrent learning aka RTRL A recurrent-network training algorithm that propagates state sensitivities to adjustable weights forward in time and contracts those sensiti…	Curated	Algorithms	`AIMech:RealTimeRecurrentLearning`	6 claims 1 source
Real-valued neural autoregressive density estimator aka RNADE, Real-valued autoregressive density estimator A fully visible neural autoregressive density architecture for real-valued vectors that shares input-to-hidden parameters across ordered sca…	Curated	Architectures	`AIMech:RealValuedNeuralAutoregressiveDensityEstimator`	1 claim 2 sources
Reasoning LLM aka Rational Large Language Model, Reasoning Large Language Model… A large language model that incorporates explicit reasoning capabilities leveraging logical rules axioms or external knowledge to make deduc…	AIO	Model	`AIO:ReasoningLLM`	Imported
Reciprocal-nearest-neighbors supported clustering aka RS clustering A hierarchical clustering algorithm that follows nearest-neighbor chains to construct sub-clustering trees around reciprocal pairs, prunes o…	Curated	Algorithms	`AIMech:ReciprocalNearestNeighborsSupportedClustering`	5 claims 1 source
Rectified Adam aka RAdam An Adam-family optimizer that rectifies its adaptive update using a time-dependent estimate of the effective history of the second-moment st…	Curated	Algorithms	`AIMech:RAdam`	1 claim 1 source
Rectified flow aka RF (rectified flow) A transport-learning method that regresses a velocity field on endpoint differences along straight interpolations of coupled samples and use…	Curated	Algorithms	`AIMech:RectifiedFlow`	2 claims 2 sources
Recurrent Layer A layer composed of recurrent units with the number equal to the hidden size of the layer.	AIO	Layer	`AIO:RecurrentLayer`	Imported
Recurrent Neural Network aka RN, RecNN… A network with connections forming a directed graph along a temporal sequence enabling dynamic behavior.	AIO	Network	`AIO:RecurrentNeuralNetwork`	Imported
Recurrent temporal restricted Boltzmann machine aka RTRBM A recurrent neural sequence architecture whose deterministic state is a conditional RBM hidden-probability vector and sets the next step’s h…	Curated	Architectures	`AIMech:RecurrentTemporalRestrictedBoltzmannMachine`	1 claim 1 source
Recursive best-first search aka RBFS A recursive search algorithm that explores the best stored subtree alternative within an upper bound and conditionally passes a previously b…	Curated	Algorithms	`AIMech:RecursiveBestFirstSearch`	2 claims 2 sources
Recursive best-first search with controlled re-expansion aka RBFS_CR, RBFS with bounded overhead An RBFS variant that estimates subtree evaluation-value distributions and inflates backed-up values to make later visits expand geometricall…	Curated	Algorithms	`AIMech:RBFSControlledReexpansion`	2 claims 2 sources
Recursive Language Model aka RLM, Compositional generalization A deep neural network that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving sys…	AIO	Network	`AIO:RecursiveLanguageModel`	Imported
Recursive LLM aka Recursive Large Language Model, Self-Attending Large Language Model… A language model that uses recursive neural network architectures like TreeLSTMs to learn syntactic composition functions improving systemat…	AIO	Model	`AIO:RecursiveLLM`	Imported
Recursive Neural Network aka RecuNN, RvNN A deep neural network that recursively applies weights over structured input to generate structured or scalar predictions.	AIO	Network	`AIO:RecursiveNeuralNetwork`	Imported
Recursive prediction-error estimation aka Recursive prediction error method A recursive parameter-estimation method that incrementally adjusts a parameterized predictor using prediction errors and search directions b…	Curated	Algorithms	`AIMech:RecursivePredictionErrorEstimation`	6 claims 1 source
Reference-family joint error rate post hoc confidence bounds aka Joint Family-Wise Error Rate Reference-Family Post Hoc Inference, JER-Controlled Reference Family Post Hoc False-Positive Bounds… A user-agnostic post hoc multiple-testing and selective-inference framework introduced by Gilles Blanchard, Pierre Neuvial, and Etienne Roqu…	Curated	Mathematical Methods	`AIMech:ReferenceFamilyJERPostHocConfidenceBounds`	4 claims 4 sources
Regression Analysis aka Regression analysis, Regression model A set of statistical processes for estimating the relationships between a dependent variable and one or more independent variables.	AIO	MachineLearningTask	`AIO:RegressionAnalysis`	Imported
Regularization Layer A layer that applies penalties on layer parameters or layer activity during optimization summed into the loss function that the network opti…	AIO	Layer	`AIO:RegularizationLayer`	Imported
Regularized Covariance Estimation by Banding aka Bickel-Levina Banded Sample Covariance and Modified Cholesky Inverse Estimator, Banding the Sample Covariance Matrix and Cholesky Factor of the Inverse… Regularized Covariance Estimation by Banding is a high-dimensional covariance and precision matrix estimation methodology for ordered p-vari…	Curated	Mathematical Methods	`AIMech:RegularizedCovarianceEstimationByBanding`	3 claims 3 sources
Regularized Evolution aka Aging Evolution An evolutionary neural-architecture search algorithm that selects a parent by recorded validation accuracy from a uniformly sampled tourname…	Curated	Algorithms	`AIMech:RegularizedEvolution`	6 claims 2 sources
Regularized information maximization aka RIM, Regularised information maximisation A discriminative clustering framework that fits conditional class probabilities by maximizing empirical input–assignment mutual information…	Curated	Algorithms	`AIMech:RegularizedInformationMaximization`	1 claim 1 source
Regularized Nonlinear Acceleration of Fixed-Point Iterations aka Scieur-d'Aspremont-Bach Regularized Nonlinear Acceleration (RNA), Tikhonov-Regularized Minimal Polynomial Extrapolation (Regularized MPE / Anderson Acceleration)… Regularized Nonlinear Acceleration of Fixed-Point Iterations (RNA) is a black-box sequence extrapolation algorithm introduced by Scieur, d'A…	Curated	Algorithms	`AIMech:RegularizedNonlinearAccelerationOfFixedPointIterations`	3 claims 3 sources
REINFORCE aka REINFORCE algorithm A family of stochastic reinforcement-learning update rules that multiply a sampled reward relative to an admissible baseline by the derivati…	Curated	Algorithms	`AIMech:REINFORCE`	3 claims 2 sources
Reinforcement Learning A machine learning task focused on methods that do not require labeled input/output pairs or explicit correction of sub-optimal actions focu…	AIO	MachineLearningTask	`AIO:ReinforcementLearning`	Imported
Reinforcement Learning LLM aka RL-Large Language Model, Reinforcement Learning Large Language Model… A large language model that is fine-tuned using reinforcement learning where the model receives rewards for generating text that satisfies c…	AIO	Model	`AIO:ReinforcementLearningLLM`	Imported
Rejection sampling aka Accept-reject sampling A random-variate generation algorithm that draws proposals from a normalized envelope dominating an unnormalized target and accepts each wit…	Curated	Algorithms	`AIMech:RejectionSampling`	1 claim 1 source
Rejection-driven independence Metropolis sampling An independence Metropolis sampler whose proposals are generated by a rejection procedure with a fixed possibly non-dominating envelope, fol…	Curated	Algorithms	`AIMech:RejectionDrivenIndependenceMetropolis`	2 claims 2 sources
Relation network A reusable neural module for relational reasoning that applies a shared learned function to pairs of object representations, sums the result…	Curated	Layers & Modules	`AIMech:RelationNetwork`	6 claims 1 source
Relative-Error CUR Matrix Decomposition via Subspace Leverage Sampling aka Subspace-Sampling Relative-Error CX and CUR Matrix Decomposition, Drineas-Mahoney-Muthukrishnan Leverage-Score CUR Decomposition… Relative-Error CUR Matrix Decomposition via Subspace Leverage Sampling is a randomized low-rank matrix factorization framework introduced by…	Curated	Algorithms	`AIMech:RelativeErrorCURMatrixDecompositionViaSubspaceLeverageSampling`	3 claims 3 sources
RelaySum Spanning-Tree Information Propagation for Decentralized Learning aka RelaySum, RelaySGD… A decentralized information propagation and model-optimization mechanism (RelaySum / RelaySGD) that routes local model updates across spanni…	Curated	Algorithms	`AIMech:RelaySumSpanningTreeInformationPropagationForDecentralizedLearning`	4 claims 3 sources
Relevance-weighted topic distillation aka Relevance-conscious topic distillation, Chakrabarti relevance-weighted distillation An iterative web-link ranking procedure that alternates authority and hub score propagation using destination relevance for forward contribu…	Curated	Algorithms	`AIMech:RelevanceWeightedTopicDistillation`	5 claims 1 source
Relevant component analysis aka RCA A partially supervised linear metric-learning procedure that estimates within-group covariance from positive equivalence constraints and whi…	Curated	Algorithms	`AIMech:RelevantComponentAnalysis`	2 claims 1 source
ReLoRA aka Restarted Low-Rank Adaptation (ReLoRA), ReLoRA High-Rank Training Through Low-Rank Updates… A parameter-efficient high-rank neural network training algorithm that transitions from an initial full-rank warm-start phase to sequential…	Curated	Algorithms	`AIMech:ReLoRA`	4 claims 3 sources
ReLU Function aka ReLU, Rectified Linear Unit A mathematical function that returns max(x 0) the element-wise maximum of 0 and the input tensor.	AIO	MathematicalFunction	`AIO:ReLUFunction`	Imported
ReLU Layer An activation layer that applies the rectified linear unit function element-wise.	AIO	Layer	`AIO:ReLULayer`	Imported
ReMixMatch A semi-supervised classifier-training procedure that adjusts weak-view guessed labels toward an estimated class prior, sharpens and anchors…	Curated	Algorithms	`AIMech:ReMixMatch`	1 claim 4 sources
Rennala SGD and Malenia SGD aka Rennala SGD, Malenia SGD… A pair of minimax time-optimal semi-asynchronous parallel stochastic gradient algorithms — Rennala SGD (Method 4, for homogeneous i.i.d. wor…	Curated	Algorithms	`AIMech:RennalaSgdAndMaleniaSgdMinimaxOptimalParallelStochasticOptimization`	4 claims 3 sources
RepAdapter (Structurally Re-parameterized Visual Adapter) aka RepAdapter, RepAdapter_attn… A parameter-efficient visual adaptation architecture that inserts a sequential linear residual bottleneck with a dense down-projection and a…	Curated	Architectures	`AIMech:RepAdapter`	4 claims 3 sources
RepeatVector Layer A reshaping layer that repeats the input n times.	AIO	Layer	`AIO:RepeatVectorLayer`	Imported
Replacing eligibility traces An eligibility-trace update that replaces a visited state’s eligibility by one while geometrically attenuating other state traces, preservin…	Curated	Mathematical Methods	`AIMech:ReplacingEligibilityTraces`	5 claims 1 source
Replicated Softmax An undirected document model with binary hidden units and a length-dependent set of categorical word units that share visible-to-hidden weig…	Curated	Architectures	`AIMech:ReplicatedSoftmax`	1 claim 1 source
Representation Bias A selection and sampling bias due to non-random sampling of subgroups making trends non-generalizable to new populations.	AIO	Bias	`AIO:RepresentationBias`	Imported
Representation Finetuning (ReFT) and Low-Rank Linear Subspace ReFT (LoReFT) aka ReFT, LoReFT… Representation Finetuning (ReFT) is a family of parameter-efficient adaptation methods for frozen language models that learns a set of non-o…	Curated	Algorithms	`AIMech:ReftAndLoreftLowRankLinearSubspaceRepresentationFinetuning`	4 claims 3 sources
Representation Learning aka Feature Learning A deep neural network that discovers representations required for feature detection or classification from raw data.	AIO	Network	`AIO:RepresentationLearning`	Imported
Rescaling Layer An image preprocessing layer that rescales input values to a new range.	AIO	Layer	`AIO:RescalingLayer`	Imported
Reshape Layer A reshaping layer that reshapes the inputs into the given shape.	AIO	Layer	`AIO:ReshapeLayer`	Imported
Reshaping Layer aka Reshape Layer A layer that is used to change the shape of the input.	AIO	Layer	`AIO:ReshapingLayer`	Imported
Residual Attention Network aka RAN (residual attention) A convolutional-network architecture that stacks attention modules combining trunk features with learned bottom-up and top-down masks throug…	Curated	Architectures	`AIMech:ResidualAttentionNetwork`	1 claim 1 source
Residual Neural Network aka DRN, Deep Residual Network… A deep neural network that employs skip connections to bypass layers facilitating learning of residual functions.	AIO	Network	`AIO:ResidualNeuralNetwork`	Imported
Resilient backpropagation aka Rprop A gradient-based optimization method that adapts coordinate step sizes using successive gradient signs and takes sign-directed parameter ste…	Curated	Algorithms	`AIMech:ResilientBackpropagation`	1 claim 1 source
Resizing Layer An image preprocessing layer that resizes images to a target size.	AIO	Layer	`AIO:ResizingLayer`	Imported
Restricted Boltzmann Machine aka RBM A Boltzmann machine network that learns the probability distribution of its input data.	AIO	Network	`AIO:RestrictedBoltzmannMachine`	Imported
Restricted Boltzmann Machine Collaborative Filtering aka RBM collaborative filtering, RBM-CF A family of shared-parameter restricted Boltzmann models for categorical user-item ratings, with a user-specific visible set and optional co…	Curated	Model Families	`AIMech:RestrictedBoltzmannMachineCollaborativeFiltering`	4 claims 1 source
Restricted Eigenvalue Properties for Correlated Gaussian Designs aka Restricted Eigenvalue Properties for Correlated Gaussian Designs (Raskutti, Wainwright, & Yu 2010), Gordon-Slepian Restricted Eigenvalue Lower Bound for Correlated Gaussian Random Designs… Restricted Eigenvalue Properties for Correlated Gaussian Designs is a high-dimensional random matrix and sparse recovery analysis framework…	Curated	Mathematical Methods	`AIMech:RestrictedEigenvaluePropertiesForCorrelatedGaussianDesigns`	3 claims 2 sources
Restricted isometry post-selection inference (PoSI) constant upper and lower bounds aka RIP-based post-selection inference (PoSI) constant bounds (Bachoc-Blanchard-Neuvial 2018), Correlation-matrix restricted isometry interpolation for universal post-selection confidence intervals… A post-selection inference methodology for linear Gaussian regression Y = mu + epsilon (epsilon ~ N(0, sigma^2 I_n)) that bounds the Berk-Br…	Curated	Mathematical Methods	`AIMech:RestrictedIsometryPostSelectionInferenceConstantBounds`	4 claims 3 sources
Retentive network aka RetNet An autoregressive neural sequence architecture that stacks pre-normalized residual blocks combining gated multi-scale retention with feedfor…	Curated	Architectures	`AIMech:RetNet`	1 claim 1 source
Retrieval-Augmented LLM aka Retrieval-Augmented Large Language Model, knowledge grounding… A large language model which combines a pre-trained language model with a retrieval system that can access external knowledge sources. This…	AIO	Model	`AIO:RetrievalAugmentedLLM`	Imported
RetroMAE (Retrieval-Oriented Masked Auto-Encoder Pre-Training) aka Retrieval-Oriented Masked Auto-Encoder, RetroMAE Pre-Training Paradigm… A retrieval-oriented self-supervised masked auto-encoder (MAE) pre-training paradigm for dense text retrieval that pollutes an input sentenc…	Curated	Learning Paradigms	`AIMech:RetroMAERetrievalOrientedMaskedAutoEncoder`	3 claims 3 sources
Reverse-submartingale confidence sequences for convex divergences and functionals aka Reverse-Submartingale Convex Functional Confidence Sequences, Exchangeable-Filtration Reverse-Stitched Divergence Confidence Sequences… A sequential nonparametric estimation and inference methodology (Manole & Ramdas 2023, IEEE Transactions on Information Theory 69(7):4641-46…	Curated	Mathematical Methods	`AIMech:ReverseSubmartingaleConvexDivergenceConfidenceSequences`	4 claims 3 sources
Reweighted wake-sleep aka RWS A learning procedure for paired generative and inference networks that uses multiple inference samples and normalized importance weights for…	Curated	Algorithms	`AIMech:ReweightedWakeSleep`	1 claim 1 source
RFA Robust Federated Aggregation via Smoothed Weiszfeld Geometric Median aka RFA, Robust Federated Aggregation… A Byzantine-robust and secure-aggregation-compatible federated learning algorithm (RFA, Algorithm 1) that replaces the weighted arithmetic m…	Curated	Algorithms	`AIMech:RfaRobustFederatedAggregationSmoothedWeiszfeldGeometricMedian`	4 claims 3 sources
RGDMult Robust Descent Using Smoothed Multiplicative Noise aka RGDMult, Robust Gradient Descent with Smoothed Multiplicative Noise… A robust first-order stochastic optimization algorithm that minimizes population risk under heavy-tailed data distributions by perturbing mo…	Curated	Algorithms	`AIMech:RGDMultRobustDescentUsingSmoothedMultiplicativeNoise`	4 claims 3 sources
Ridge Regression A regression analysis that estimates the coefficients of multiple regression models in scenarios where the independent variables are highly…	AIO	MachineLearningTask	`AIO:RidgeRegression`	Imported
Riondato–Kornaropoulos fixed-sample betweenness approximation aka RK betweenness approximation, Riondato–Kornaropoulos betweenness sampling A fixed-sample graph betweenness approximation algorithm that chooses a sample count using a VC-dimension bound for shortest-path incidence…	Curated	Algorithms	`AIMech:RiondatoKornaropoulosBetweennessSampling`	6 claims 1 source
Ritter–Gallegos two-stage outlier-mixture fitting aka POP–BAS–OUT mixture fitting A two-stage mixture-parameter fitting procedure that estimates a regular component from a threshold-selected basic subset of a contaminated…	Curated	Algorithms	`AIMech:RitterGallegosTwoStageOutlierMixtureFitting`	4 claims 1 source
RLPrompt Reinforcement Learning Discrete Prompt Optimization aka RLPrompt, Reinforcement Learning Discrete Text Prompt Optimization… A gradient-free discrete text prompt optimization algorithm that formulates prompt construction z = [z_1, ..., z_T] in V^T as a sequential r…	Curated	Algorithms	`AIMech:RLPromptReinforcementLearningDiscretePromptOptimization`	4 claims 3 sources
RLR Robust Learning Rate Sign-Voting Backdoor Defense for Federated Learning aka Robust Learning Rate for Federated Learning, RLR Federated Backdoor Defense… A server-side federated learning backdoor defense that adjusts the server's learning rate vector eta_theta in {+eta, -eta}^d coordinate-wise…	Curated	Algorithms	`AIMech:RlrRobustLearningRateSignVotingBackdoorDefenseForFederatedLearning`	4 claims 3 sources
RMSprop An adaptive gradient optimization method that normalizes coordinate updates using an exponentially weighted estimate of squared gradients.	Curated	Algorithms	`AIMech:RMSprop`	1 claim 1 source
RNN Layer The base class for recurrent layers.	AIO	Layer	`AIO:RNNLayer`	Imported
RNN-NADE aka Recurrent neural network neural autoregressive distribution estimator A neural sequence architecture in which a deterministic recurrent state supplies parameters of a NADE output distribution, combining tempora…	Curated	Architectures	`AIMech:RecurrentNeuralNetworkNeuralAutoregressiveDistributionEstimator`	1 claim 2 sources
RNN-RBM aka Recurrent neural network restricted Boltzmann machine A neural sequence architecture in which a deterministic recurrent network with its own hidden state supplies parameters of a conditional RBM…	Curated	Architectures	`AIMech:RecurrentNeuralNetworkRestrictedBoltzmannMachine`	1 claim 1 source
Robust adaptive Metropolis aka RAM An adaptive random-walk Metropolis algorithm that updates the proposal shape factor by a rank-one transformation driven by the proposal dire…	Curated	Algorithms	`AIMech:RobustAdaptiveMetropolis`	1 claim 1 source
Robust continuous clustering aka RCC clustering A clustering algorithm that optimizes one representative per observation using squared data fidelity and robust attraction along a neighborh…	Curated	Algorithms	`AIMech:RobustContinuousClustering`	6 claims 5 sources
ROCK clustering aka ROCK, Robust Clustering using linKs An agglomerative clustering procedure that merges clusters using shared-neighbor link counts divided by a cluster-size normalization derived…	Curated	Algorithms	`AIMech:ROCKClustering`	1 claim 1 source
RocketQA (Cross-Batch and Denoised Hard Negative Dense Passage Retrieval Training) aka RocketQA Dense Passage Retrieval Training, RocketQA Denoised Hard Negative Pipeline… A four-step multi-stage training algorithm for dual-encoder dense passage retrieval that (1) trains an initial dual-encoder M_D^(0) on label…	Curated	Algorithms	`AIMech:RocketQADenoisedHardNegativeSampling`	3 claims 3 sources
RocketQAv2 Joint Training for Dense Passage Retrieval and Passage Reranking aka RocketQAv2, RocketQAv2 Dynamic Listwise Distillation and Hybrid Data Augmentation… A joint training algorithm for dense passage retrieval and passage reranking that couples a bi-encoder dual-encoder retriever s_de(q, p) = E…	Curated	Algorithms	`AIMech:RocketQAv2JointTrainingDensePassageRetrievalAndReranking`	4 claims 3 sources
Role-author-recipient-topic model aka RART A family of message-content models in which actors have latent-role distributions and ordered sender-role/recipient-role pairs determine top…	Curated	Model Families	`AIMech:RoleAuthorRecipientTopicModel`	2 claims 1 source
RoSA aka Robust Adaptation, Robust Low-Rank and Sparse Adaptation… An additive parameter-efficient fine-tuning algorithm inspired by robust principal component analysis that jointly trains a low-rank adapter…	Curated	Algorithms	`AIMech:RoSA`	4 claims 3 sources
rsLoRA aka Rank-Stabilized LoRA, Rank-Stabilized Low-Rank Adaptation… A rank-stabilized low-rank adaptation algorithm that scales the low-rank adapter product BA by gamma_r = alpha / sqrt(r) instead of the conv…	Curated	Algorithms	`AIMech:RsLoRA`	4 claims 3 sources
RVMD Reduced-Order Variational Mode Decomposition aka Reduced-Order Variational Mode Decomposition, RVMD Spatiotemporal Modal Decomposition… A spatiotemporal modal decomposition and dimensionality reduction algorithm that represents a high-dimensional space-time field q(x, t) as a…	Curated	Algorithms	`AIMech:RVMDReducedOrderVariationalModeDecomposition`	4 claims 3 sources
s-Bucketing for Agnostic Byzantine-Robust Aggregation on Heterogeneous Datasets aka s-Bucketing for Byzantine-Robust Aggregation, ARAGG Bucketing… A randomized pre-aggregation meta-algorithm proposed by Karimireddy, He, and Jaggi (ICLR 2022) that adapts classical IID Byzantine-robust ag…	Curated	Algorithms	`AIMech:BucketingForAgnosticByzantineRobustAggregationOnHeterogeneousDatasets`	4 claims 3 sources
S-LoRA aka Scalable LoRA Serving with Unified Paging, S-LoRA Concurrent Multi-Adapter Serving A scalable multi-adapter inference serving algorithm and memory management architecture that decouples batched base-model computation from o…	Curated	Algorithms	`AIMech:SLoRA`	5 claims 3 sources
SamplePairing An image-classification augmentation procedure that averages an anchor image with a randomly selected training image using equal pixel weigh…	Curated	Algorithms	`AIMech:SamplePairing`	1 claim 1 source
SARAH Stochastic Recursive Gradient for Finite-Sum Optimization aka StochAstic Recursive grAdient algoritHm (SARAH), SARAH and SARAH+ Recursive Variance-Reduced Gradient Method… SARAH Stochastic Recursive Gradient for Finite-Sum Optimization is a variance-reduced first-order stochastic optimization algorithm and prac…	Curated	Algorithms	`AIMech:SARAHStochasticRecursiveGradientForFiniteSumOptimization`	3 claims 3 sources
Sarsa aka State-action-reward-state-action An on-policy temporal-difference control algorithm that updates the current state-action value toward the observed reward plus the discounte…	Curated	Algorithms	`AIMech:Sarsa`	1 claim 2 sources
SAWB Statistics-Aware Weight Binning Quantization aka SAWB, Statistics-Aware Weight Binning… A low-bitwidth neural network weight quantization algorithm that determines the symmetric clipping threshold alpha_w* minimizing weight quan…	Curated	Algorithms	`AIMech:SAWBStatisticsAwareWeightBinningQuantization`	4 claims 3 sources
SCAFFOLD Stochastic Controlled Averaging for Heterogeneous Federated Learning aka SCAFFOLD, Stochastic Controlled Averaging for Federated Learning… A federated optimization algorithm (SCAFFOLD) that eliminates client drift across N heterogeneous clients by maintaining a local control var…	Curated	Algorithms	`AIMech:ScaffoldStochasticControlledAveragingForFederatedLearning`	4 claims 3 sources
Scaled Gradient Descent (ScaledGD) for Ill-Conditioned Low-Rank Matrix and Tensor Estimation aka ScaledGD, Scaled Gradient Descent for Low-Rank Matrix and Tensor Estimation… A right-preconditioned nonconvex factored optimization methodology (introduced by Tian Tong, Cong Ma, and Yuejie Chi in 2021) that eliminate…	Curated	Algorithms	`AIMech:ScaledGradientDescentForIllConditionedLowRankMatrixEstimation`	3 claims 3 sources
Scaled LASSO and Huber Concomitant Penalized Joint Sparse Regression aka Scaled Lasso, Scaled Sparse Linear Regression… Scaled LASSO and Huber Concomitant Penalized Joint Sparse Regression is a high-dimensional sparse linear regression and noise-level estimati…	Curated	Algorithms	`AIMech:ScaledLassoAndHuberConcomitantPenalizedJointSparseRegression`	3 claims 3 sources
Scaled Legendre HiPPO operator aka HiPPO-LegS The HiPPO projection operator using the uniform measure over the full elapsed interval from zero to the current time, with scaled-Legendre c…	Curated	Mathematical Methods	`AIMech:HiPPOLegS`	1 claim 1 source
Scaling & Shifting Your Features aka SSF, SSF-ADA… A parameter-efficient fine-tuning algorithm (SSF) for pre-trained deep neural networks (including Vision Transformers, hierarchical Transfor…	Curated	Algorithms	`AIMech:SSFScaleAndShiftFeatures`	3 claims 3 sources
Schedule-Free Optimization (Schedule-Free SGD and Schedule-Free AdamW) aka Schedule-Free Optimization, Schedule-Free SGD… A family of anytime stochastic optimization algorithms (Schedule-Free SGD, Equations 3-5, and Schedule-Free AdamW, Algorithm 1) and an onlin…	Curated	Algorithms	`AIMech:ScheduleFreeOptimizationViaIterateAveragingAndMomentumInterpolation`	4 claims 3 sources
Scheduled sampling An autoregressive sequence-training procedure that chooses between reference and model-produced previous outputs as feedback, using a schedu…	Curated	Algorithms	`AIMech:ScheduledSampling`	6 claims 2 sources
SCSG (Stochastically Controlled Stochastic Gradient) for Non-Convex Optimization aka SCSG, Non-Convex SCSG… A variance-reduced stochastic optimization algorithm (Lei, Ju, Chen, & Jordan 2017) for smooth non-convex finite-sum and online optimization…	Curated	Algorithms	`AIMech:ScsgStochasticallyControlledStochasticGradientForNonconvexOptimization`	3 claims 3 sources
Searching and Sampling Uniform Confidence Intervals for Invalid Instruments aka Searching and Sampling Confidence Intervals for Invalid Instruments, RobustIV Searching and Sampling… A post-selection-robust causal-inference methodology (introduced by Zijian Guo in 2023) for constructing uniformly valid confidence interval…	Curated	Algorithms	`AIMech:SearchingAndSamplingUniformConfidenceIntervalsForInvalidInstruments`	3 claims 3 sources
Seasonal Autoregressive Integrated Moving-Average aka SARIMA A model that extends ARIMA, explicitly supporting univariate time series data with a seasonal component, combining seasonal differencing wit…	AIO	Model	`AIO:SeasonalAutoregressiveIntegratedMovingAverage`	Imported
SEED Pre-Training a Strong Text Encoder Using a Weak Decoder aka SEED-Encoder, SEED Weak-Decoder Pre-Training for Dense Retrieval… A representation-bottleneck encoder-decoder pre-training architecture for dense text retrieval (SEED-Encoder) that encodes a masked input pa…	Curated	Architectures	`AIMech:SEEDPreTrainingStrongTextEncoderUsingWeakDecoder`	4 claims 3 sources
SeLa aka Self-labelling via simultaneous clustering and representation learning, Self-labeling via simultaneous clustering and representation learning A self-supervised representation-learning procedure that alternates neural pseudo-label prediction and dataset-wide self-labelling through a…	Curated	Algorithms	`AIMech:SeLa`	1 claim 3 sources
Selection And Sampling Bias aka Sampling Bias, Selection Bias… A computational bias introduced by non-random selection of individuals groups or data failing to ensure representativeness.	AIO	Bias	`AIO:SelectionAndSamplingBias`	Imported
Selective Adherence Bias An individual bias characterized by the tendency to selectively adopt algorithmic advice that matches pre-existing beliefs and stereotypes.	AIO	Bias	`AIO:SelectiveAdherenceBias`	Imported
Selectively traversed accumulation rules for structured false discovery rate control aka STAR Framework for Interactive Structured Multiple Testing, Selectively Traversed Accumulation Rules (STAR)… An interactive multiple-testing methodology (Lei, Ramdas, & Fithian 2021, Biometrika 108(2):253-267, arXiv:1710.02776) that controls the fal…	Curated	Mathematical Methods	`AIMech:SelectivelyTraversedAccumulationRulesForStructuredFDRControl`	4 claims 3 sources
Self-Adaptive In-Context Learning aka Self-Adaptive ICL, TopK+MDL In-Context Example Selection and Ordering… An instance-level two-stage select-then-rank algorithm for in-context learning (TopK+MDL) that first narrows the training pool to a small se…	Curated	Algorithms	`AIMech:SelfAdaptiveInContextLearning`	4 claims 3 sources
Self-Concordant and Pseudo-Self-Concordant Finite-Sample M-Estimation aka Finite-Sample Analysis of M-Estimators Using Self-Concordance, Canonically Self-Concordant and Pseudo-Self-Concordant Empirical Risk Minimization… Self-Concordant and Pseudo-Self-Concordant Finite-Sample M-Estimation is a non-asymptotic statistical estimation and excess-risk analysis me…	Curated	Mathematical Methods	`AIMech:SelfConcordantAndPseudoSelfConcordantFiniteSampleMEstimation`	4 claims 3 sources
Self-consistency and dependency control framework for false discovery rate control aka Blanchard-Roquain Self-Consistency and Dependency Control Framework, SC and DC Conditions for Weighted False Discovery Rate Control… A modular mathematical framework for multiple hypothesis testing on any countable (or continuous) hypothesis space H equipped with a finite…	Curated	Mathematical Methods	`AIMech:SelfConsistencyAndDependencyControlFDRFramework`	4 claims 3 sources
Self-Normalized Heteroscedastic LASSO Optimal Instrumental Variables and Weak-Identification Sup-Score Inference aka Self-Normalized Heteroscedastic LASSO and Post-LASSO for Optimal Instruments, BCCH Sparse Optimal Instrumental Variables and Sup-Score Test… A high-dimensional sparse instrumental variable (IV) estimation and inference framework (introduced by Alexandre Belloni, Daniel Chen, Victo…	Curated	Algorithms	`AIMech:SelfNormalizedHeteroscedasticLassoOptimalInstrumentalVariablesAndWeakIdentificationSupScoreInference`	3 claims 3 sources
Self-supervised Learning A machine learning task that is intermediate between supervised and unsupervised learning and predicts parts of the input data from other ob…	AIO	MachineLearningTask	`AIO:SelfsupervisedLearning`	Imported
Self-Supervised LLM aka Pretext tasks A large language model which learns rich representations by solving pretext tasks that involve predicting parts of the input from other obse…	AIO	Model	`AIO:SelfSupervisedLLM`	Imported
Self-Tuning Pivotal High-Dimensional Instrumental Variables (STIV) and Sensitivity-Based Confidence Sets aka Self-Tuning Instrumental Variables Estimator (STIV), Gautier-Tsybakov-Rose High-Dimensional Instrumental Variables Estimator… A self-normalized, scale-invariant convex conic methodology for high-dimensional linear instrumental variables regression $Y = X^\top \beta…	Curated	Algorithms	`AIMech:SelfTuningPivotalHighDimensionalInstrumentalVariablesAndSensitivityConfidenceSets`	3 claims 3 sources
SELU Function aka SELU, Scaled Exponential Linear Unit A mathematical function that multiplies scale (> 1) with the output of the ELU function to ensure a slope larger than one for positive input…	AIO	MathematicalFunction	`AIO:SELUFunction`	Imported
Semi-Supervised LLM aka Semi-Supervised Large Language Model, self-training A large language model which combines self-supervised pretraining on unlabeled data with supervised fine-tuning on labeled task data.	AIO	Model	`AIO:SemiSupervisedLLM`	Imported
Semidefinite Maximum Margin Clustering aka Xu2004 Maximum Margin Clustering A binary clustering procedure that relaxes latent label-equivalence matrices to a convex semidefinite program for a fixed-kernel soft-margin…	Curated	Algorithms	`AIMech:SemidefiniteMaximumMarginClustering`	4 claims 1 source
Semiparametric linear programming regression aka Semiparametric LP regression A supervised regression algorithm that jointly fits a finite kernel expansion and an unpenalized supplied parametric basis by minimizing fix…	Curated	Algorithms	`AIMech:SemiparametricLinearProgrammingRegression`	6 claims 1 source
Semiparametric support vector regression aka Semiparametric SV regression A supervised regression algorithm that jointly fits an unpenalized finite expansion of supplied basis functions and a kernel component, mini…	Curated	Algorithms	`AIMech:SemiparametricSupportVectorRegression`	7 claims 1 source
Semisupervised Semidefinite Maximum Margin Clustering aka Xu2004 Semisupervised Maximum Margin Clustering A semisupervised binary margin-learning procedure that adds observed-label pair constraints and labeled-to-unlabeled linkage constraints to…	Curated	Algorithms	`AIMech:SemisupervisedSemidefiniteMaximumMarginClustering`	6 claims 1 source
Separable Natural Evolution Strategies The Gaussian population natural evolution strategy that samples independent normal coordinates, ranks their evaluated fitness, and adapts th…	Curated	Algorithms	`AIMech:SeparableNaturalEvolutionStrategies`	6 claims 1 source
Separable Nonnegative Matrix Factorization and Robust-Loner Recovery aka Separable NMF, Arora-Ge-Kannan-Moitra Separable NMF and Robust-Loner Algorithm… Separable Nonnegative Matrix Factorization and Robust-Loner Recovery is a polynomial-time provable factorization framework introduced by Aro…	Curated	Algorithms	`AIMech:SeparableNonnegativeMatrixFactorizationAndRobustLonerRecovery`	3 claims 3 sources
SeparableConvolution1D Layer aka SeparableConv1D Layer A convolutional layer that performs depthwise separable 1D convolution.	AIO	Layer	`AIO:SeparableConvolution1DLayer`	Imported
SeparableConvolution2D Layer aka SeparableConv2D Layer A convolutional layer that performs depthwise separable 2D convolution.	AIO	Layer	`AIO:SeparableConvolution2DLayer`	Imported
Separator-node conflict diagnostic A Bayesian graphical-model diagnostic that duplicates a selected separator node or node vector, partitions the information informing it, and…	Curated	Algorithms	`AIMech:SeparatorNodeConflictDiagnostic`	7 claims 1 source
Sequential kernelized independence testing by betting aka SKIT, Sequential Hilbert-Schmidt Independence Criterion Test by Betting… A sequential nonparametric independence hypothesis testing framework (Podkopaev, Blobaum, Kasiviswanathan, & Ramdas 2023, ICML / PMLR 202:27…	Curated	Mathematical Methods	`AIMech:SequentialKernelizedIndependenceTestingByBetting`	4 claims 3 sources
Sequential Model-based Algorithm Configuration aka SMAC A sequential algorithm-configuration procedure that uses random-forest performance models to propose parameter settings and compares candida…	Curated	Algorithms	`AIMech:SequentialModelBasedAlgorithmConfiguration`	1 claim 1 source
Sequential nonparametric quantile confidence sequences aka Anytime-Valid Nonparametric Quantile Confidence Sequences, Time-Uniform Empirical Distribution Function and Quantile Bands… A distribution-free, nonasymptotic sequential estimation and hypothesis testing framework (Howard & Ramdas 2022) for arbitrary fixed quantil…	Curated	Mathematical Methods	`AIMech:SequentialNonparametricQuantileConfidenceSequences`	4 claims 3 sources
Sequential score-discrepancy conflict diagnostic aka Sequential score-based node conflict check, Two-stage parent-child score conflict diagnostic A two-stage Bayesian directed acyclic graph (DAG) node-conflict diagnostic algorithm that partitions observed data around a selected separat…	Curated	Algorithms	`AIMech:SequentialScoreDiscrepancyConflictDiagnostic`	5 claims 2 sources
Set Transformer A neural encoder-decoder architecture for permutation-invariant set-input prediction that uses attention to encode interactions among elemen…	Curated	Architectures	`AIMech:SetTransformer`	1 claim 1 source
Set Transformer++ aka ST++ A Set Transformer architecture revision that replaces its induced-attention encoder blocks with set-normalized blocks retaining identity res…	Curated	Architectures	`AIMech:SetTransformerPlusPlus`	1 claim 1 source
Sever Spectral Gradient Filtering Meta-Algorithm for Robust Stochastic Optimization aka Sever Robust Meta-Algorithm for Stochastic Optimization, Sever Spectral Outlier Gradient Filtering… An outlier-robust stochastic optimization meta-algorithm that iteratively invokes a black-box gamma-approximate learner L on the current act…	Curated	Algorithms	`AIMech:SeverSpectralGradientFilteringMetaAlgorithmForRobustStochasticOptimization`	4 claims 3 sources
Shake-Shake regularization The original residual-network training and inference procedure that combines two learned branch outputs with complementary uniform random we…	Curated	Algorithms	`AIMech:ShakeShakeRegularization`	6 claims 1 source
ShakeDrop regularization A residual-network regularization procedure that uses a Bernoulli switch to alternate ordinary residual computation with separately specifie…	Curated	Algorithms	`AIMech:ShakeDropRegularization`	6 claims 2 sources
Shampoo (Preconditioned Stochastic Tensor Optimization) aka Shampoo, Shampoo Optimizer… A structure-aware preconditioned stochastic optimization algorithm over order-k tensor parameter spaces R^{n_1 x ... x n_k} that maintains a…	Curated	Algorithms	`AIMech:ShampooPreconditionedStochasticTensorOptimization`	4 claims 3 sources
SHapley additive explanations aka SHAP An additive feature-attribution framework assigning Shapley values to a prediction through a specified function for evaluating feature subse…	Curated	Mathematical Methods	`AIMech:SHAP`	1 claim 1 source
Shared inverse-lengthscale variational sparse-spectrum inference The Tan–Ong–Nott–Jasra sparse-spectrum regression inference procedure that alternates a Gaussian nonconjugate variational proposal for a sha…	Curated	Algorithms	`AIMech:SharedInverseLengthscaleVariationalSparseSpectrumInference`	7 claims 2 sources
Shift-and-Invert Preconditioning for Faster Leading Eigenvector Computation aka Garber-Hazan-Jin-Kakade-Musco-Netrapalli-Sidford Shift-and-Invert PCA, Shifted-and-Inverted Power Method with Sum-of-Non-Convex SVRG… Shift-and-Invert Preconditioning for Faster Leading Eigenvector Computation is a matrix-free spectral estimation framework introduced by Gar…	Curated	Algorithms	`AIMech:ShiftAndInvertPreconditioningForFasterEigenvectorComputation`	3 claims 3 sources
Short-Dot Coded Sparse Dot Products for Straggler-Resilient Linear Transforms aka Short-Dot, Short-Dot Codes… A straggler-resilient coded parallelization method for computing large linear transforms A x (with A in R^{M x N} and input x in R^N across…	Curated	Algorithms	`AIMech:ShortDotCodedSparseDotProductsForStragglerResilientLinearTransforms`	3 claims 3 sources
Sieve-Streaming and Sieve-Streaming++ for Single-Pass Monotone Submodular Maximization aka Sieve-Streaming and Sieve-Streaming++, Badanidiyuru-Mirzasoleiman-Karbasi-Krause Sieve-Streaming… Sieve-Streaming and Sieve-Streaming++ for Single-Pass Monotone Submodular Maximization are single-pass streaming data summarization algorith…	Curated	Algorithms	`AIMech:SieveStreamingAndSieveStreamingPlusPlusForSubmodularMaximization`	3 claims 3 sources
Sigmoid belief network aka SBN A directed acyclic probabilistic network of binary variables whose forward conditional probabilities are logistic functions of weighted pare…	Curated	Architectures	`AIMech:SigmoidBeliefNetwork`	1 claim 1 source
Sigmoid Function aka tore A mathematical function that applies the sigmoid activation function sigmoid(x) = 1 / (1 + exp(-x)) always returning a value between 0 and 1…	AIO	MathematicalFunction	`AIO:SigmoidFunction`	Imported
SignGuard Norm-Based and Sign-Clustering Malicious Gradient Filtering aka SignGuard, SignGuard Collaborative Malicious Gradient Filtering… A Byzantine-robust federated gradient aggregation algorithm proposed by Xu, Huang, Song, and Lan (2022) that defends distributed learning ag…	Curated	Algorithms	`AIMech:SignGuardNormAndSignClusteringMaliciousGradientFiltering`	4 claims 3 sources
signSGD and Majority-Vote Compressed Non-Convex Optimization aka signSGD, Majority-Vote signSGD… A 1-bit gradient-compression and non-convex stochastic optimization framework (Bernstein, Wang, Azizzadenesheli, & Anandkumar 2018) that upd…	Curated	Algorithms	`AIMech:SignSgdAndMajorityVoteCompressedNonconvexOptimization`	3 claims 3 sources
SimCLR aka Simple framework for contrastive learning of visual representations A self-supervised representation-learning procedure that jointly trains an encoder and a nonlinear projection head by contrasting two augmen…	Curated	Algorithms	`AIMech:SimCLR`	1 claim 1 source
Simes closed-testing concentration-set shortcut and double-asymptotic false discovery proportion consistency aka Goeman-Meijer-Krebs-Solari exact Simes closed-testing FDP shortcut, Simes closed-testing concentration set Z_alpha… Simes closed-testing concentration-set shortcut and double-asymptotic false discovery proportion (FDP) consistency is the multiple-testing m…	Curated	Mathematical Methods	`AIMech:SimesClosedTestingConcentrationShortcutAndDoubleAsymptoticFDPConsistency`	4 claims 3 sources
SimLM Representation-Bottleneck Replaced Language Model Pre-Training aka SimLM, Similarity Matching with Language Model Pre-Training… A self-supervised pre-training algorithm and bottleneck architecture for dense passage retrieval that corrupts an input passage x twice usin…	Curated	Algorithms	`AIMech:SimLMRepresentationBottleneckPreTraining`	4 claims 3 sources
SimNet aka SimNets A neural architecture family built from learned template-similarity operations and MEX log-mean-exp operations that combine shifted similari…	Curated	Architectures	`AIMech:SimNet`	8 claims 2 sources
Simple recursive best-first search aka SRBFS A recursive best-first search procedure that initializes generated children from their static evaluation values, explores the best child wit…	Curated	Algorithms	`AIMech:SimpleRecursiveBestFirstSearch`	2 claims 2 sources
SimpleRNN Layer A recurrent layer that implements a fully-connected RNN where the output is to be fed back to input.	AIO	Layer	`AIO:SimpleRNNLayer`	Imported
SimpleRNNCell Layer A layer that processes one step within the whole time sequence input for a SimpleRNN layer.	AIO	Layer	`AIO:SimpleRNNCellLayer`	Imported
Simplified memory-bounded A-star search aka SMA* A node-budgeted best-first tree-search algorithm that generates one successor at a time, propagates evaluation values through pathmax and co…	Curated	Algorithms	`AIMech:SimplifiedMemoryBoundedAStar`	4 claims 1 source
Simplified TinyBERT (Knowledge Distillation for Document Retrieval) aka Simplified TinyBERT, Simplified TinyBERT for Document Retrieval… A knowledge distillation method for passage-level BERT-MaxP document re-ranking (Chen, He, Hui, Sun, & Sun, ECIR 2021) that simplifies TinyB…	Curated	Learning Paradigms	`AIMech:SimplifiedTinyBERTKnowledgeDistillationForDocumentRetrieval`	4 claims 3 sources
Simpson's Paradox Bias aka Simpson's Paradox A selection and sampling bias where the association between two variables changes when controlling for another variable.	AIO	Bias	`AIO:SimponsParadoxBias`	Imported
SimSiam A self-supervised representation-learning procedure that trains a shared encoder and predictor to match the encoder output of another augmen…	Curated	Algorithms	`AIMech:SimSiam`	1 claim 1 source
Simulated annealing A stochastic optimization procedure that explores candidate configurations with temperature-controlled acceptance of cost-increasing moves a…	Curated	Algorithms	`AIMech:SimulatedAnnealing`	2 claims 2 sources
Simultaneous normal-equation post-selection confidence regions in model-free linear regression aka Model-Free Normal-Equation PoSI Confidence Regions, Assumption-Lean Simultaneous Normal-Equation Confidence Regions (R_hat_{n,M}, R_hat_{n,M}^dagger)… Simultaneous normal-equation post-selection confidence regions in model-free linear regression are an assumption-lean statistical inference…	Curated	Mathematical Methods	`AIMech:SimultaneousNormalEquationPostSelectionConfidenceRegions`	4 claims 3 sources
Simultaneous pathwise false discovery proportion bounds aka Simultaneous High-Probability FDP Bounds Across Nested Rejection Paths, Closed-Testing Interpolation-Based Simultaneous FDP Control… A finite-sample multiple-testing and selective-inference methodology (Katsevich & Ramdas 2020, The Annals of Statistics 48(6):3465-3487, arX…	Curated	Mathematical Methods	`AIMech:SimultaneousPathwiseFalseDiscoveryProportionBounds`	4 claims 3 sources
Single-step parametric maxT inference A simultaneous-inference procedure for a declared family of linear functions of model parameters that standardizes joint estimates and uses…	Curated	Algorithms	`AIMech:SingleStepParametricMaxTInference`	7 claims 1 source
Singular Value Thresholding Algorithm for Matrix Completion aka Singular Value Thresholding, SVT Algorithm for Matrix Completion… Singular Value Thresholding Algorithm for Matrix Completion (SVT) is a first-order primal-dual Uzawa/linearized-Bregman optimization method…	Curated	Algorithms	`AIMech:SingularValueThresholdingAlgorithmForMatrixCompletion`	3 claims 3 sources
Sinkhorn Distances and Entropic Regularized Optimal Transport aka Sinkhorn Distance, Dual-Sinkhorn Entropic Optimal Transport… Sinkhorn Distances and Entropic Regularized Optimal Transport is a scalable optimal transport framework introduced by Cuturi (2013) that rep…	Curated	Algorithms	`AIMech:SinkhornDistancesAndEntropicRegularizedOptimalTransport`	3 claims 3 sources
Sketchy (Frequent-Directions Sketched Adaptive Regularization / S-AdaGrad and S-Shampoo) aka Sketchy Optimizer, S-AdaGrad… A memory-efficient matrix-preconditioned adaptive optimization framework—instantiated as Sketchy AdaGrad (S-AdaGrad) for vector parameters a…	Curated	Algorithms	`AIMech:SketchyFrequentDirectionsAdaptiveRegularizationOptimization`	5 claims 3 sources
SLEDGE (SciBERT Zero-Shot Domain-Transfer Scientific Literature Search) aka SLEDGE, SLEDGE Scientific Knowledge Search… A two-stage zero-shot domain-transfer scientific literature retrieval and neural re-ranking methodology (MacAvaney, Cohan, & Goharian, EMNLP…	Curated	Architectures	`AIMech:SLEDGESciBERTZeroShotScientificLiteratureSearch`	4 claims 3 sources
Slice sampling An auxiliary-variable Monte Carlo method that augments a target density with a uniform height below its graph and updates the state using a…	Curated	Algorithms	`AIMech:SliceSampling`	1 claim 1 source
SlowMo (Slow Momentum for Communication-Efficient Distributed SGD) aka SlowMo, Slow Momentum for Communication-Efficient Distributed SGD… A general two-timescale distributed optimization wrapper (Wang et al. 2020, Section 2, Algorithm 1) in which m workers independently execute…	Curated	Algorithms	`AIMech:SlowMoSlowMomentumForCommunicationEfficientDistributedSgd`	4 claims 3 sources
SLSGD Secure Local Stochastic Gradient Descent with Trimmed Mean and Moving Average aka SLSGD, Secure Local Stochastic Gradient Descent… A Byzantine-resilient communication-efficient distributed on-device optimization algorithm proposed by Xie, Koyejo, and Gupta (ECML-PKDD 201…	Curated	Algorithms	`AIMech:SlsgdSecureLocalStochasticGradientDescentWithTrimmedMeanAndMovingAverage`	4 claims 3 sources
SM3 (Square-root of Minima of Sums of Maxima of Squared-gradients Method) aka SM3 Optimizer, Square-root of Minima of Sums of Maxima of Squared-gradients Method… A memory-efficient adaptive gradient optimization algorithm (Algorithms SM3-I and SM3-II) that covers the d model parameters with k nonempty…	Curated	Algorithms	`AIMech:SM3SquareRootMinimaSumsMaximaSquaredGradientsOptimization`	4 claims 3 sources
Smart Augmentation A learned augmentation procedure that trains a network to synthesize examples from same-class inputs while receiving both a within-class ref…	Curated	Algorithms	`AIMech:SmartAugmentation`	1 claim 1 source
SMITH: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching aka SMITH Hierarchical Document Matching Encoder, Siamese Multi-depth Transformer-based Hierarchical Encoder… A two-tower Siamese ('Dual-Encoder') hierarchical Transformer architecture for long-to-long document semantic matching (Yang, Zhang, Li, Ben…	Curated	Architectures	`AIMech:SMITHSiameseMultiDepthTransformerBasedHierarchicalEncoder`	3 claims 3 sources
SmoothGrad A sensitivity-map smoothing method that averages maps computed on Gaussian-noise perturbations of an input.	Curated	Algorithms	`AIMech:SmoothGrad`	1 claim 1 source
SMOTE-NC The original mixed nominal/continuous extension of SMOTE that synthesizes minority-class training examples by finding minority neighbors wit…	Curated	Preprocessing Methods	`AIMech:SMOTENC`	6 claims 1 source
SNVRG (Stochastic Nested Variance Reduction) for Non-Convex Optimization aka SNVRG, Stochastic Nested Variance Reduction… Stochastic Nested Variance Reduction (SNVRG) is a multi-level hierarchical variance-reduced stochastic gradient algorithm for non-convex fin…	Curated	Algorithms	`AIMech:SnvrgStochasticNestedVarianceReductionForNonconvexOptimization`	3 claims 3 sources
SOAP (ShampoO with Adam in the Preconditioner's Eigenbasis) aka SOAP, SOAP Optimizer… A second-order stochastic optimization algorithm (ShampoO with Adam in the Preconditioner's eigenbasis) that maintains Kronecker-factored gr…	Curated	Algorithms	`AIMech:SoapShampooWithAdamInPreconditionerEigenbasis`	4 claims 3 sources
Societal Bias A systemic bias characterized by being for or against groups or individuals based on social identities demographic factors or immutable phys…	AIO	Bias	`AIO:SocietalBias`	Imported
Soft actor-critic aka SAC An off-policy actor-critic algorithm fitting a stochastic policy and soft value functions under a reward-plus-policy-entropy objective.	Curated	Algorithms	`AIMech:SoftActorCritic`	1 claim 1 source
Soft Q-learning The 2017 maximum-entropy continuous-control learning algorithm that fits neural soft action values from replayed transitions and trains an a…	Curated	Algorithms	`AIMech:SoftQLearning`	6 claims 3 sources
Soft-Impute Iterative Soft-Thresholded SVD for Large Matrix Completion aka Soft-Impute Nuclear-Norm Regularized Matrix Completion (Mazumder-Hastie-Tibshirani), Iterative Soft-Thresholded SVD EM/MM Algorithm for Incomplete Matrices… Soft-Impute Iterative Soft-Thresholded SVD for Large Matrix Completion is a convex spectral-regularization and majorization-minimization (EM…	Curated	Algorithms	`AIMech:SoftImputeIterativeSoftThresholdedSVDForLargeMatrixCompletion`	3 claims 3 sources
Softmax Function A mathematical function where the elements of the output vector are in range (0 1) and sum to 1 and each vector is handled independently.	AIO	MathematicalFunction	`AIO:SoftmaxFunction`	Imported
Softmax Layer An activation layer that applies the softmax function to the inputs.	AIO	Layer	`AIO:SoftmaxLayer`	Imported
Softplus Function A mathematical function that is softplus(x) = log(exp(x) + 1).	AIO	MathematicalFunction	`AIO:SoftplusFunction`	Imported
Softsign Function A mathematical function that is softsign(x) = x / (abs(x) + 1).	AIO	MathematicalFunction	`AIO:SoftsignFunction`	Imported
Some Invalid Some Valid Instrumental Variables Estimator (sisVIVE) and 50% Majority-Rule Identifiability aka sisVIVE, Some Invalid Some Valid Instrumental Variables Estimator… An $\ell_1$-penalized instrumental variables methodology and structural identifiability theory (introduced by Hyunseung Kang, Anru Zhang, T.…	Curated	Algorithms	`AIMech:SomeInvalidSomeValidInstrumentalVariablesEstimatorAndMajorityRuleIdentifiability`	3 claims 3 sources
Sophia (Second-Order Clipped Stochastic Optimization) aka Sophia Optimizer, Sophia-G… A scalable second-order stochastic optimization algorithm (Algorithm 1) designed for large-scale language model pre-training that preconditi…	Curated	Algorithms	`AIMech:SophiaSecondOrderClippedStochasticOptimization`	4 claims 3 sources
SoRA (Sparse Low-Rank Adaptation) aka Sparse Low-Rank Adaptation, SoRA Proximal-Gradient Adaptive-Rank LoRA… An adaptive-rank parameter-efficient fine-tuning algorithm that initializes low-rank adaptation matrices W_d in R^{r_max x q} and W_u in R^{…	Curated	Algorithms	`AIMech:SoRASparseLowRankAdaptation`	4 claims 3 sources
SoteriaFL Unified Framework for Private Federated Learning with Shifted Communication Compression aka SoteriaFL, Soteria-SGD… A unified framework for local differentially private (LDP) federated learning with communication compression (Algorithm 1) in which each cli…	Curated	Algorithms	`AIMech:SoteriaFlUnifiedFrameworkForPrivateFederatedLearningWithShiftedCommunicationCompression`	4 claims 3 sources
Space-Alternating Generalized Expectation Maximization aka SAGE Algorithm, Space-Alternating GEM A generalized expectation-maximization method that updates selected parameter blocks using block-specific hidden-data spaces or valid object…	Curated	Algorithms	`AIMech:SpaceAlternatingGeneralizedExpectationMaximization`	4 claims 3 sources
Sparse additive generative model aka SAGE A generative model family for categorical text data that forms word probabilities by normalizing a background log-frequency vector plus spar…	Curated	Model Families	`AIMech:SparseAdditiveGenerativeModel`	1 claim 1 source
Sparse Auto Encoder aka SAE, Sparse AE… An autoencoder network with more hidden units than inputs that constrains only a few hidden units to be active at once.	AIO	Network	`AIO:SparseAutoEncoder`	Imported
Sparse Expectation Maximization aka Sparse EM An EM variant that updates relative latent-state probabilities within selected plausible sets while preserving their total mass and all outs…	Curated	Algorithms	`AIMech:SparseExpectationMaximization`	3 claims 1 source
Sparse Learning aka Sparse coding, Sparse dictionary Learning A representation learning network that finds sparse representations of input data as a linear combination of basic elements and identifies t…	AIO	Network	`AIO:SparseLearning`	Imported
Sparse LLM aka Sparse Large Language Model, model compression… A large language model that uses techniques like pruning or quantization to reduce the number of non-zero parameters in the model making it…	AIO	Model	`AIO:SparseLLM`	Imported
Sparse pachinko allocation inference aka pruned PAM Gibbs sampling An approximate pachinko-allocation fitting procedure that restricts token path resampling to currently active document topics and word-assoc…	Curated	Algorithms	`AIMech:SparsePachinkoAllocationInference`	3 claims 1 source
Sparse Permutation Invariant Covariance Estimation aka SPICE, Sparse Permutation-Invariant Concentration Matrix Estimator… Sparse Permutation Invariant Covariance Estimation (SPICE) is a high-dimensional inverse covariance (concentration) matrix estimation method…	Curated	Mathematical Methods	`AIMech:SparsePermutationInvariantCovarianceEstimation`	3 claims 3 sources
Sparse Principal Components Analysis via Coordinate-Variance Subset Selection and Thresholding aka Johnstone-Lu Adaptive Sparse Principal Components Analysis, ASPCA Coordinate-Variance Subset Selection and Wavelet Thresholding… Sparse Principal Components Analysis via Coordinate-Variance Subset Selection and Thresholding (ASPCA) is a high-dimensional principal compo…	Curated	Mathematical Methods	`AIMech:SparsePrincipalComponentsAnalysisViaCoordinateVarianceSelectionAndThresholding`	3 claims 3 sources
Sparse-spectrum Gaussian-process exact moment matching aka SSGP-EMM An uncertain-input prediction algorithm that analytically integrates sine/cosine feature moments of a fixed sparse-spectrum Gaussian-process…	Curated	Algorithms	`AIMech:SparseSpectrumGaussianProcessExactMomentMatching`	5 claims 3 sources
Sparse-spectrum Gaussian-process linearized uncertain-input prediction aka SSGP-Lin A local uncertain-input prediction algorithm for a fixed sparse-spectrum Gaussian-process posterior that linearizes the posterior mean at th…	Curated	Algorithms	`AIMech:SparseSpectrumGaussianProcessLinearizedPrediction`	5 claims 4 sources
Sparse-spectrum Gaussian-process regression aka SSGP, Sparse spectrum Gaussian process A Gaussian-process regression model family whose latent prior is a finite sum of paired sine and cosine features with independent Gaussian c…	Curated	Model Families	`AIMech:SparseSpectrumGaussianProcessRegression`	6 claims 2 sources
Sparsified Stochastic Gradient Descent with Error Memory for k-Contractive Gradient Compression aka Mem-SGD, Sparsified SGD with Memory… An error-compensated stochastic gradient descent optimization algorithm (Mem-SGD) that compresses each step's scaled stochastic gradient plu…	Curated	Algorithms	`AIMech:SparsifiedSgdWithErrorMemoryForKContractiveGradientCompression`	4 claims 3 sources
SPARTA Sparse Transformer Matching for Retrieval aka SPARTA, Sparse Transformer Matching… A sparse neural retrieval architecture for open-domain and sentence-level question answering that encodes each query q = [t_1, ..., t_\|q\|] v…	Curated	Architectures	`AIMech:SPARTASparseTransformerMatchingForRetrieval`	4 claims 3 sources
SparTerm Learning Term-Based Sparse Representation for Fast Text Retrieval aka SparTerm, SparTerm Sparse Representation Framework… A term-based sparse retrieval representation framework that maps an input text p into a vocabulary-sized sparse vector p' = F(p) odot G(p) i…	Curated	Architectures	`AIMech:SparTermLearningTermBasedSparseRepresentation`	4 claims 3 sources
Spatial Regression A regression analysis used to model spatial relationships.	AIO	MachineLearningTask	`AIO:SpatialRegression`	Imported
Spatial Transformer aka Spatial Transformer module A learnable neural-network component that predicts an input-dependent spatial transformation and uses the resulting sampling grid to warp an…	Curated	Layers & Modules	`AIMech:SpatialTransformer`	2 claims 2 sources
SpatialDropout1D Layer A regularization layer that performs the same function as Dropout but drops entire 1D feature maps instead of individual elements.	AIO	Layer	`AIO:SpatialDropout1DLayer`	Imported
SpatialDropout2D Layer A regularization layer that performs the same function as Dropout but drops entire 2D feature maps instead of individual elements.	AIO	Layer	`AIO:SpatialDropout2DLayer`	Imported
SpatialDropout3D Layer A regularization layer that performs the same function as Dropout but drops entire 3D feature maps instead of individual elements.	AIO	Layer	`AIO:SpatialDropout3DLayer`	Imported
Speaker-Adaptive Training LHUC aka SAT-LHUC An acoustic-model training procedure that jointly learns shared network parameters, training-speaker hidden-unit contribution transforms and…	Curated	Algorithms	`AIMech:SpeakerAdaptiveTrainingLHUC`	5 claims 1 source
Speaker-Dependent Pooling Adaptation An acoustic-model adaptation procedure that updates a small set of pooling parameters for a target speaker using decoded acoustic targets wh…	Curated	Algorithms	`AIMech:SpeakerDependentPoolingAdaptation`	5 claims 1 source
Spectral hashing An unsupervised binary-code learning algorithm that approximates a spectral similarity-preservation objective using a PCA-aligned rectangula…	Curated	Algorithms	`AIMech:SpectralHashing`	1 claim 1 source
Spectral Observable Operator Algorithm (LEARN-HMM) for Learning Hidden Markov Models aka Hsu-Kakade-Zhang Spectral HMM Learning Algorithm (LEARN-HMM), Observable Operator Model Spectral HMM Estimation… A polynomial-time spectral method-of-moments algorithm (LEARN-HMM, introduced by Daniel Hsu, Sham M. Kakade, and Tong Zhang in 2009/2012) fo…	Curated	Algorithms	`AIMech:SpectralObservableOperatorAlgorithmForLearningHiddenMarkovModels`	4 claims 3 sources
SPIDER Stochastic Path-Integrated Differential Estimator for Non-Convex Optimization aka Stochastic Path-Integrated Differential EstimatoR (SPIDER), SPIDER-SFO and SPIDER-SFO+ Non-Convex Stochastic Optimization… SPIDER Stochastic Path-Integrated Differential Estimator for Non-Convex Optimization is a martingale variance-reduction tracking framework a…	Curated	Algorithms	`AIMech:SPIDERStochasticPathIntegratedDifferentialEstimatorForNonConvexOptimization`	3 claims 3 sources
SpiderBoost and Proximal SpiderBoost with Momentum for Non-Convex Optimization aka SpiderBoost, Prox-SpiderBoost… A family of stochastic path-integrated variance reduction algorithms (Wang, Ji, Zhou, Liang, & Tarokh 2019) for smooth and composite non-con…	Curated	Algorithms	`AIMech:SpiderBoostAndProximalSpiderBoostWithMomentumForNonconvexOptimization`	3 claims 3 sources
Spiking Hidden Layer A hidden layer that makes connections to an additional, heterogeneous hidden layer; modeled after biological neural networks.	AIO	Layer	`AIO:SpikingHiddenLayer`	Imported
SPLADE (Sparse Lexical and Expansion Model for First Stage Ranking) aka SParse Lexical AnD Expansion Model, SPLADE First-Stage Sparse Retriever… A learned sparse neural information retrieval architecture for first-stage inverted-index ranking that maps an input query or document token…	Curated	Architectures	`AIMech:SPLADESparseLexicalAndExpansionModel`	3 claims 3 sources
Split-Mix Federated Learning aka Split-Mix, Split-Mix FL… A model-heterogeneous federated learning and in-situ customization algorithm (Split-Mix; Hong, Wang, Wang, and Zhou, ICLR 2022) that decompo…	Curated	Algorithms	`AIMech:SplitMixHeterogeneousWidthSubnetworkFederatedLearning`	4 claims 3 sources
SplitFed Learning aka SplitFed, SFL… A hybrid distributed collaborative machine learning algorithm and dual-server split-network architecture (SplitFed / SFL; Thapa, Chamikara,…	Curated	Algorithms	`AIMech:SplitFedFederatedAndSplitLearningHybridArchitecture`	4 claims 3 sources
SPoT (Soft Prompt Transfer) aka Soft Prompt Transfer, SPoT Prompt Transfer… A parameter-efficient prompt-based transfer learning methodology for frozen pre-trained language models that introduces an intermediate sour…	Curated	Algorithms	`AIMech:SPoTSoftPromptTransfer`	4 claims 3 sources
Square root graphical model aka SQR, Square root Markov random field A family of finite undirected graphical probability models that retains univariate base measures while coupling specified square roots of su…	Curated	Model Families	`AIMech:SquareRootGraphicalModel`	1 claim 2 sources
Square-Root LASSO Pivotal Second-Order Cone Sparse Regression aka Square-Root Lasso, Sqrt-LASSO Pivotal Sparse Recovery… Square-Root LASSO Pivotal Second-Order Cone Sparse Regression is a high-dimensional sparse linear regression estimator introduced by Belloni…	Curated	Algorithms	`AIMech:SquareRootLassoPivotalConicSparseRegression`	3 claims 3 sources
Squeeze-and-Excitation block aka SE block A neural-network feature recalibration component that globally averages each channel, transforms the resulting descriptor through a learned…	Curated	Layers & Modules	`AIMech:SqueezeAndExcitationBlock`	1 claim 1 source
Stack-augmented recurrent neural network aka Stack RNN A recurrent sequence architecture whose neural controller reads the leading entries of one or more external stack states and learns continuo…	Curated	Architectures	`AIMech:StackAugmentedRecurrentNeuralNetwork`	6 claims 3 sources
StackedRNNCells Layer A layer that allows a stack of RNN cells to behave as a single cell.	AIO	Layer	`AIO:StackedRNNCellsLayer`	Imported
Stacking aka Stacked generalization Ensemble learning that trains a final estimator on base-estimator predictions.	Curated	Algorithms	`AIMech:Stacking`	1 claim 1 source
Stein variational gradient descent An interacting-particle inference algorithm that approximates a differentiable continuous target by synchronously transporting particles wit…	Curated	Algorithms	`AIMech:SteinVariationalGradientDescent`	5 claims 3 sources
Stein Variational Policy Gradient aka SVPG A policy optimization method that applies Stein variational gradient descent to an entropy-regularized distribution over policy parameters,…	Curated	Algorithms	`AIMech:SteinVariationalPolicyGradient`	6 claims 2 sources
STEM (Stochastic Two-Sided Momentum for Federated Learning) aka STEM, Stochastic Two-Sided Momentum… A federated non-convex stochastic optimization algorithm (Khanduri et al. 2021, Section 2, Algorithm 1, Equations 2-5) in which each client…	Curated	Algorithms	`AIMech:StemStochasticTwoSidedMomentumForFederatedLearning`	4 claims 3 sources
Step-up-down least favorable configuration and two-population Steck false discovery rate bounds aka Blanchard-Dickhaus-Roquain-Villers Step-Up-Down LFC Framework, Two-Population Generalized Steck's Recursion for Step-Up-Down FDR… A finite-sample and non-asymptotic statistical multiple-testing framework developed by Gilles Blanchard, Thorsten Dickhaus, Etienne Roquain,…	Curated	Mathematical Methods	`AIMech:StepUpDownLeastFavorableConfigurationFDRBounds`	4 claims 4 sources
Stepping-out slice sampling A univariate slice-sampling algorithm that randomly places a width-w interval around the current point, expands it in width-w steps under a…	Curated	Algorithms	`AIMech:SteppingOutSliceSampling`	1 claim 1 source
Stigmergy A computational coordination mechanism in which actions modify an accessible environment or medium and those changes influence subsequent ac…	Curated	Coordination Mechanisms	`AIMech:Stigmergy`	5 claims 2 sources
Stochastic Approximation Expectation Maximization aka SAEM, Stochastic Approximation EM An incomplete-data fitting method that recursively averages simulated complete-data log objectives or sufficient statistics using a step-siz…	Curated	Algorithms	`AIMech:StochasticApproximationExpectationMaximization`	4 claims 2 sources
Stochastic beam search aka SBS The sequence-sampling algorithm of Kool, van Hoof and Welling that implements Gumbel-Top-k without replacement implicitly on a locally norma…	Curated	Algorithms	`AIMech:StochasticBeamSearch`	3 claims 2 sources
Stochastic Block Model Exact Recovery Phase Transition and Semidefinite Programming aka SBM Exact Recovery Phase Transition, Abbe-Bandeira-Hall SBM Phase Transition… Stochastic Block Model Exact Recovery Phase Transition and Semidefinite Programming is the information-theoretic and convex-optimization fra…	Curated	Mathematical Methods	`AIMech:StochasticBlockModelExactRecoveryPhaseTransitionAndSemidefiniteProgramming`	3 claims 3 sources
Stochastic Cubic Regularization for Fast Nonconvex Optimization aka Tripuraneni-Stern-Jin-Regier-Jordan Stochastic Cubic Regularized Newton Method, Hessian-Vector Product Stochastic Cubic Regularization… Stochastic Cubic Regularization for Fast Nonconvex Optimization is a Hessian-free (Hessian-vector-product based) stochastic second-order opt…	Curated	Algorithms	`AIMech:StochasticCubicRegularizationForFastNonconvexOptimization`	3 claims 3 sources
Stochastic depth A residual-network training procedure that randomly bypasses residual transformations during training and uses all residual transformations…	Curated	Algorithms	`AIMech:StochasticDepth`	1 claim 1 source
Stochastic Expectation Maximization aka Stochastic EM, SEM (stochastic expectation maximization) A finite-mixture fitting algorithm that draws one hard component assignment for each observation from its current posterior responsibilities…	Curated	Algorithms	`AIMech:StochasticExpectationMaximization`	4 claims 2 sources
Stochastic factorized variational sparse-spectrum Gaussian-process inference aka sfVSSGP The Gal–Turner stochastic extension of factorized variational sparse-spectrum regression that estimates its full-data evidence lower bound w…	Curated	Algorithms	`AIMech:StochasticFactorizedVariationalSparseSpectrumGaussianProcessInference`	5 claims 3 sources
Stochastic gradient descent aka SGD Optimization using gradients estimated from sampled training observations.	Curated	Algorithms	`AIMech:StochasticGradientDescent`	1 claim 1 source
Stochastic Gradient Push and Overlap SGP (SGP and tau-OSGP for Distributed Deep Learning) aka Stochastic Gradient Push, SGP and Overlap SGP… An asymmetric push-only decentralized stochastic optimization algorithm over time-varying B-strongly-connected column-stochastic mixing matr…	Curated	Algorithms	`AIMech:StochasticGradientPushAndOverlapSgpForDistributedDeepLearning`	4 claims 3 sources
Stochastic learning automata A family of adaptive stochastic decision procedures that selects an action from a maintained finite action-probability vector, receives eval…	Curated	Learning Paradigms	`AIMech:StochasticLearningAutomata`	6 claims 1 source
Stochastic local search A configurable family of combinatorial search algorithms that initializes a search position and any memory, then applies a specified neighbo…	Curated	Algorithms	`AIMech:StochasticLocalSearch`	6 claims 2 sources
Stochastic nonconjugate GLMM variational inference A finite-population Bayesian GLMM inference procedure that iterates selected cluster-local Gaussian factors and uses expanded cluster miniba…	Curated	Algorithms	`AIMech:StochasticNonconjugateGLMMVariationalInference`	7 claims 2 sources
Stochastic Polyak Step-Size aka SPS, SPS_max… An adaptive learning-rate selection rule for stochastic gradient descent on finite-sum or streaming objectives min_{x in R^d} f(x) = (1 / n)…	Curated	Algorithms	`AIMech:StochasticPolyakStepSize`	4 claims 3 sources
Stochastic Pooling A spatial neural pooling layer that samples one activation per region with probability proportional to its nonnegative value during training…	Curated	Layers & Modules	`AIMech:StochasticPooling`	5 claims 1 source
Stochastic-Greedy Linear-Time Monotone Submodular Maximization aka Lazier Than Lazy Greedy (Stochastic-Greedy), Mirzasoleiman-Badanidiyuru-Karbasi-Vondrak-Krause Stochastic-Greedy Algorithm… Stochastic-Greedy Linear-Time Monotone Submodular Maximization is a randomized combinatorial optimization algorithm introduced by Mirzasolei…	Curated	Algorithms	`AIMech:StochasticGreedyLinearTimeMonotoneSubmodularMaximization`	3 claims 3 sources
Stochastic-times-smooth unit aka STS unit A stochastic activation that sets p=sigmoid(a), samples a Bernoulli gate with success probability sqrt(p), and outputs the gate multiplied b…	Curated	Mathematical Methods	`AIMech:StochasticTimesSmoothUnit`	1 claim 1 source
STORM (Stochastic Recursive Momentum) for Single-Loop Adaptive Variance-Reduced Non-Convex SGD aka STORM, STOchastic Recursive Momentum… STOchastic Recursive Momentum (STORM) is a single-loop, checkpoint-free, adaptive variance-reduced stochastic gradient descent algorithm for…	Curated	Algorithms	`AIMech:StormStochasticRecursiveMomentumForNonconvexOptimization`	3 claims 3 sources
Straight-through estimator aka ST estimator, Identity straight-through estimator A surrogate-gradient rule that keeps a hard threshold or sampled binary output in the forward computation while propagating its downstream d…	Curated	Mathematical Methods	`AIMech:StraightThroughEstimator`	3 claims 1 source
Straight-through Gumbel-Softmax estimator aka ST Gumbel-Softmax, ST Gumbel estimator A surrogate-gradient estimator that uses a hard one-hot argmax of a Gumbel-Softmax sample in the forward computation and substitutes the cor…	Curated	Mathematical Methods	`AIMech:StraightThroughGumbelSoftmax`	2 claims 1 source
Strategic oscillation A search-control strategy that alternates search directions or regimes around selected boundaries, controlling excursions and returns to exp…	Curated	Algorithms	`AIMech:StrategicOscillation`	1 claim 2 sources
Streetlight Effect Bias aka Streetlight Effect An individual bias where people search only where it is easiest to look.	AIO	Bias	`AIO:StreetlightEffectBias`	Imported
Strict Saddle Property and Noisy Stochastic Gradient Saddle Escaping for Orthogonal Tensor Decomposition aka Strict Saddle Property and Noisy SGD Saddle Escaping (Ge-Huang-Jin-Yuan 2015), Projected Noisy Stochastic Gradient Descent on Strict Saddle Manifolds… The geometric characterization of $(\theta,\gamma,\zeta)$-strict saddle functions (both unconstrained in $\mathbb{R}^d$ and manifold-constra…	Curated	Algorithms	`AIMech:StrictSaddlePropertyAndNoisyStochasticGradientSaddleEscapingForOrthogonalTensorDecomposition`	4 claims 3 sources
StringLookup Layer A categorical features preprocessing layer that maps string features to integer indices.	AIO	Layer	`AIO:StringLookupLayer`	Imported
STRIPS planning method A symbolic planning method that uses means–ends analysis and theorem proving over world models to construct a sequence of operators satisfyi…	Curated	Algorithms	`AIMech:STRIPSPlanning`	1 claim 1 source
Structurally constrained recurrent neural network aka SCRN, SCRNN A recurrent sequence architecture coupling a nonlinear recurrent hidden state with a separate linear context state whose recurrence is const…	Curated	Architectures	`AIMech:StructurallyConstrainedRecurrentNeuralNetwork`	6 claims 5 sources
Structure-Aware Intrinsic Dimension (SAID) aka SAID Subspace Fine-Tuning, Structure Aware Intrinsic Dimension… A subspace fine-tuning and intrinsic-dimensionality measurement methodology for pre-trained neural networks that reparameterizes m-layer par…	Curated	Algorithms	`AIMech:SAIDStructureAwareIntrinsicDimension`	4 claims 3 sources
Structured mean-field inference aka Structured mean-field approximation A variational inference method that approximates a target distribution with a tractable family retaining selected dependencies, choosing its…	Curated	Mathematical Methods	`AIMech:StructuredMeanFieldInference`	1 claim 1 source
Structured state space sequence model aka S4 A structured linear state-space sequence model whose normal-plus-low-rank state matrix is transformed to diagonal-plus-low-rank form for eff…	Curated	Model Families	`AIMech:S4`	1 claim 1 source
Structured variational inference for factorial HMMs aka Structured mean-field inference for factorial HMMs A variational inference procedure for factorial hidden Markov models that approximates the posterior by independent chain-path distributions…	Curated	Algorithms	`AIMech:StructuredVariationalInferenceForFactorialHMMs`	1 claim 1 source
Sub-Cluster Component clustering aka Sub-Cluster Component algorithm An agglomerative clustering algorithm that repeatedly merges weakly connected components of a thresholded nearest-neighbor graph over the cu…	Curated	Algorithms	`AIMech:SubClusterComponentClustering`	7 claims 1 source
Sub-psi uniform boundary confidence sequences aka Time-Uniform Nonparametric Nonasymptotic Sub-Psi Confidence Sequences, Polynomial Stitched Sub-Gamma Uniform Boundary (S_alpha)… A general nonparametric, nonasymptotic sequential estimation and boundary-crossing framework (Howard, Ramdas, McAuliffe, & Sekhon 2021) for…	Curated	Mathematical Methods	`AIMech:SubPsiUniformBoundaryConfidenceSequences`	4 claims 3 sources
Sublinear Poisson graphical model aka SPGM, Sublinear Poisson Markov random field A finite-graph model for unbounded nonnegative integer counts that retains factorial base measures while replacing counts in unary and pairw…	Curated	Model Families	`AIMech:SublinearPoissonGraphicalModel`	1 claim 2 sources
Submodular pick LIME aka SP-LIME A method selecting a budgeted set of local LIME explanations by greedily increasing weighted coverage of explanatory features.	Curated	Algorithms	`AIMech:SPLIME`	1 claim 1 source
Subsampled Randomized Hadamard Transform Subspace Embedding aka SRHT Oblivious Subspace Embedding, Subsampled Randomized Walsh-Hadamard Transform (SRHT)… Subsampled Randomized Hadamard Transform Subspace Embedding is a structured fast oblivious dimension-reduction operator Phi = sqrt(n / l) R…	Curated	Mathematical Methods	`AIMech:SubsampledRandomizedHadamardTransformSubspaceEmbedding`	3 claims 3 sources
Subspace Pursuit for Compressive Sensing Signal Reconstruction aka Subspace Pursuit, SP Algorithm for Compressive Sensing… Subspace Pursuit for Compressive Sensing Signal Reconstruction (SP) is an iterative backtracking greedy algorithm introduced by Dai and Mile…	Curated	Algorithms	`AIMech:SubspacePursuitForCompressiveSensingSignalReconstruction`	3 claims 3 sources
Subtract Layer A merging layer that subtracts two inputs.	AIO	Layer	`AIO:SubtractLayer`	Imported
Subword Segmentation aka Fragmentation, Part-word Division… A data preparation that divides text into subword units which are smaller than words but larger than individual characters to improve the ef…	AIO	Preprocessing	`AIO:SubwordSegmentation`	Imported
Successive Halving aka SHA, Sequential Halving A staged best-candidate selection algorithm that divides a resource budget across elimination rounds, evaluates surviving candidates with co…	Curated	Algorithms	`AIMech:SuccessiveHalving`	1 claim 2 sources
Sunk Cost Fallacy Bias aka Sunk Cost Fallacy A bias characterized by the tendency to continue an endeavor due to previously invested resources despite costs outweighing benefits.	AIO	Bias	`AIO:SunkCostFallacyBias`	Imported
Supermasks in Superposition aka SupSup, HopSupSup… A continual learning algorithm that eliminates catastrophic forgetting by keeping a shared base neural network fixed at random signed-Kaimin…	Curated	Algorithms	`AIMech:SupSupSupermasksInSuperposition`	4 claims 3 sources
Supervised Biclustering aka Supervised Block Clustering, Supervised Co-clustering… A biclustering task focused on methods that simultaneously cluster the rows and columns of a labeled matrix considering data labels to enhan…	AIO	MachineLearningTask	`AIO:SupervisedBiclustering`	Imported
Supervised Clustering aka Supervised Cluster Analysis A clustering focused on methods that group labeled objects such that objects in the same group have similar labels relative to those in othe…	AIO	MachineLearningTask	`AIO:SupervisedClustering`	Imported
Supervised Learning A machine learning task focused on methods that learn a function mapping input to output based on example input-output pairs.	AIO	MachineLearningTask	`AIO:SupervisedLearning`	Imported
Supervised Principal Components aka Supervised Principal Components Regression A prediction procedure that screens features by their marginal association with an outcome, computes principal components of the retained fe…	Curated	Algorithms	`AIMech:SupervisedPrincipalComponents`	4 claims 1 source
Supplemented Expectation Conditional Maximization aka Supplemented ECM, SECM A numerical supplement to expectation conditional maximization that recovers observed-data asymptotic parameter covariance from expected com…	Curated	Algorithms	`AIMech:SupplementedExpectationConditionalMaximization`	4 claims 1 source
Supplemented Expectation Maximization aka Supplemented EM, SEM Algorithm (Supplemented EM) A numerical supplement to expectation maximization that combines expected complete-data information with the local Jacobian of the EM update…	Curated	Algorithms	`AIMech:SupplementedExpectationMaximization`	3 claims 1 source
Support Vector Clustering aka SVC An unsupervised clustering procedure that fits a soft enclosing sphere to observations in Gaussian-kernel feature space, then labels retaine…	Curated	Algorithms	`AIMech:SupportVectorClustering`	7 claims 1 source
Support vector data description aka SVDD, Support vector domain description… A one-class support-estimation algorithm that learns a sphere in an input or kernel feature space by minimizing squared radius plus linearly…	Curated	Algorithms	`AIMech:SupportVectorDataDescription`	6 claims 3 sources
Support Vector Machine aka SVM, SVN… A network with supervised learning models for classification and regression that maps training examples to points in space maximizing the ga…	AIO	Network	`AIO:SupportVectorMachine`	Imported
Survival Analysis A machine learning task focused on methods for analyzing the expected duration of time until one or more events occur such as death in biolo…	AIO	MachineLearningTask	`AIO:SurvivalAnalysis`	Imported
Survivorship Bias A processing bias characterized by the tendency to focus on items observations or people that "survive" a selection process overlooking thos…	AIO	Bias	`AIO:SurvivorshipBias`	Imported
Swapout A stochastic neural-network training and inference procedure that forms elementwise Bernoulli-selected sums of already computed compatible t…	Curated	Algorithms	`AIMech:Swapout`	6 claims 1 source
Swarm intelligence A computational design paradigm, in the broadened 1999 formulation, that develops algorithms or distributed problem-solving devices inspired…	Curated	Computational Paradigms	`AIMech:SwarmIntelligence`	5 claims 1 source
SWATS aka Switching from Adam to SGD Optimization Strategy, Gradient-Subspace Projected Adam-to-SGD Hybrid Optimizer… A hyperparameter-free hybrid stochastic optimization strategy (Switching from Adam to SGD) that begins training in an Adam phase, estimates…	Curated	Algorithms	`AIMech:SWATS`	4 claims 3 sources
SwAV aka Swapping assignments between views An online self-supervised visual representation-learning procedure that predicts soft prototype assignments of one augmented image view from…	Curated	Algorithms	`AIMech:SwAV`	1 claim 2 sources
Swish Function A mathematical function that is x*sigmoid(x) a smooth non-monotonic function that consistently matches or outperforms ReLU on deep networks.	AIO	MathematicalFunction	`AIO:SwishFunction`	Imported
Symmetric delayed rejection aka Symmetric delaying rejection algorithm The delayed-rejection specialization using the same symmetric proposal kernel at every stage, centered through the last rejected candidate,…	Curated	Algorithms	`AIMech:SymmetricDelayedRejection`	1 claim 1 source
Symmetrically Connected Network aka SCN A network that is a type of recurrent neural network where connections between units are symmetrical with equal weights in both directions.	AIO	Network	`AIO:SymmetricallyConnectedNetwork`	Imported
SyncBatchNorm Layer aka SyncBatchNorm A batch normalization layer that applies synchronous Batch Normalization across multiple devices.	AIO	Layer	`AIO:SyncBatchNormLayer`	Imported
Synthetic Minority Over-sampling Technique aka SMOTE A minority-class oversampling method that generates synthetic labeled feature vectors by interpolating between an observed minority example…	Curated	Preprocessing Methods	`AIMech:SyntheticMinorityOversamplingTechnique`	1 claim 1 source
Systemic Bias A bias resulting from procedures and practices of systems that operate in ways which result in certain social groups being advantaged or fav…	AIO	Bias	`AIO:SystemicBias`	Imported
t-Distributed Stochastic Neighbor embedding aka t-SNE, tSNE A dimensionality reduction for visualizing high-dimensional data by giving each datapoint a location in a two or three-dimensional map.	AIO	MachineLearningTask	`AIO:tDistributedStochasticNeighborembedding`	Imported
T-Few Fine-Tuning aka T-Few A few-shot classification fine-tuning recipe that adapts a pretrained T0 model through IA3 activation vectors, multitask pretraining of thos…	Curated	Algorithms	`AIMech:TFewFineTuning`	5 claims 2 sources
Tabu search aka TS A memory-guided optimization framework that steers a search trajectory by making selected moves temporarily inadmissible from search history…	Curated	Algorithms	`AIMech:TabuSearch`	1 claim 1 source
Tabu search for SAT (TSAT) The SAT-specific basic tabu-search method described by Mazure, Saïs and Grégoire in 1997, which systematically excludes recently flipped var…	Curated	Algorithms	`AIMech:TabuSearchForSAT`	5 claims 2 sources
TAMUNA Doubly Accelerated Distributed Optimization with Local Training, Compression, and Partial Participation aka TAMUNA, TAMUNA Doubly Accelerated Distributed Optimization under Partial Participation… A federated and distributed optimization algorithm introduced by Condat, Agarský, Malinovsky, and Richtárik (2023) that simultaneously combi…	Curated	Algorithms	`AIMech:TamunaDoublyAcceleratedDistributedOptimizationWithLocalTrainingCompressionAndPartialParticipation`	4 claims 3 sources
Tanh Function aka hyperbolic tangent A mathematical function that is the hyperbolic tangent activation function.	AIO	MathematicalFunction	`AIO:TanhFunction`	Imported
TART (Task-Aware Retrieval with Instructions) aka Task-Aware ReTriever, Task-Aware Retrieval with Instructions… A multi-task instruction-following information retrieval methodology that conditions document relevance scoring on both the user query q and…	Curated	Algorithms	`AIMech:TARTTaskAwareRetrievalWithInstructions`	3 claims 3 sources
TAS-Balanced Topic-Aware Sampling and Dual-Teacher Margin Distillation aka TAS-B, TAS-Balanced… A resource-efficient training and batch-sampling algorithm for single-vector dual-encoder dense retrieval (BERT_DOT) that clusters all train…	Curated	Algorithms	`AIMech:TASBTopicAwareSamplingBalancedMarginDistillation`	4 claims 3 sources
Taylor approximation for uncertain-input Gaussian-process prediction aka Taylor Gaussian-process uncertainty propagation A local Gaussian-process prediction algorithm that expands a fixed posterior mean to first order and its latent variance to second order abo…	Curated	Algorithms	`AIMech:GaussianProcessTaylorUncertainInputPrediction`	5 claims 3 sources
TCT-ColBERT Tightly-Coupled Teachers Knowledge Distillation for Dense Retrieval aka TCT-ColBERT, Tightly-Coupled Teacher ColBERT… A knowledge-distillation algorithm for single-stage dense passage retrieval that initializes a Siamese BERT bi-encoder student from a fine-t…	Curated	Algorithms	`AIMech:TCTColBERTTightlyCoupledTeachersForDenseRetrieval`	4 claims 3 sources
Teacher Assistant Knowledge Distillation (TAKD) aka TAKD, Teacher Assistant Knowledge Distillation… A multi-step knowledge distillation paradigm that mitigates accuracy degradation caused by a large capacity gap between a high-capacity teac…	Curated	Learning Paradigms	`AIMech:TAKDTeacherAssistantKnowledgeDistillation`	4 claims 3 sources
Teacher forcing A sequence-training procedure that supplies reference outputs from earlier steps as feedback for subsequent predictions, in place of the mod…	Curated	Algorithms	`AIMech:TeacherForcing`	6 claims 2 sources
Tempered expectation maximization aka Tempered EM An entropy-tempered generalization of expectation maximization for finite latent-state models that alternates powered latent-joint responsib…	Curated	Algorithms	`AIMech:TemperedExpectationMaximization`	1 claim 1 source
Tempered transitions aka Neal tempered transitions A Markov chain Monte Carlo transition algorithm that proposes a new target state through a prescribed outward and return sequence of mutuall…	Curated	Algorithms	`AIMech:TemperedTransitions`	6 claims 2 sources
Temporal Bias A selection and sampling bias arising from differences in populations and behaviors over time.	AIO	Bias	`AIO:TemporalBias`	Imported
Temporal ensembling A semi-supervised classifier-training procedure that regularizes a current stochastic prediction toward a bias-corrected exponential average…	Curated	Algorithms	`AIMech:TemporalEnsembling`	1 claim 2 sources
Temporal factored restricted Boltzmann machine language model aka Temporal FRBM A sequential extension of the factored RBM language model that directs information from the preceding binary hidden state into the current h…	Curated	Architectures	`AIMech:TemporalFactoredRestrictedBoltzmannMachineLanguageModel`	1 claim 2 sources
Temporal restricted Boltzmann machine aka TRBM A neural sequence architecture that multiplies time-indexed conditional RBM distributions whose visible and hidden biases depend on precedin…	Curated	Architectures	`AIMech:TemporalRestrictedBoltzmannMachine`	1 claim 2 sources
Temporal-difference learning aka TD learning A family of prediction-learning methods that assign temporal credit using discrepancies between successive, recursively related predictions…	Curated	Learning Paradigms	`AIMech:TemporalDifferenceLearning`	2 claims 2 sources
Temporal-kernel recurrent neural network aka TKRNN A recurrent architecture that factors connections across time into learned spatial weights and source-specific exponential temporal kernels,…	Curated	Architectures	`AIMech:TemporalKernelRecurrentNeuralNetwork`	6 claims 1 source
Tensor Normal Training (TNT Kronecker-Factored Natural Gradient Optimization) aka Tensor Normal Training, TNT Optimizer… A structure-aware second-order natural gradient optimization algorithm for deep neural networks that approximates each layer's block-diagona…	Curated	Algorithms	`AIMech:TensorNormalTrainingKroneckerNaturalGradientOptimization`	5 claims 3 sources
Tensor Spectral Decomposition of Centered 3-Star Graph Moments for Dirichlet Mixed-Membership Community Models aka Tensor Spectral Approach to Mixed Membership Stochastic Blockmodels (MMSB), Anandkumar-Ge-Hsu-Kakade Centered 3-Star Tensor Community Detection… Tensor Spectral Decomposition of Centered 3-Star Graph Moments for Dirichlet Mixed-Membership Community Models is a guaranteed polynomial-ti…	Curated	Algorithms	`AIMech:TensorSpectralDecompositionForDirichletMixedMembershipCommunityModels`	3 claims 3 sources
TERM (Tilted Empirical Risk Minimization and Hierarchical Multi-Objective Tilting) aka TERM, Tilted Empirical Risk Minimization… A parametric family of exponentially tilted risk minimization objectives and batch/stochastic first-order solvers (Li, Beirami, Sanjabi, & S…	Curated	Algorithms	`AIMech:TermTiltedEmpiricalRiskMinimizationAndHierarchicalMultiObjectiveTilting`	4 claims 3 sources
TernGrad (Stochastic Ternary Gradient Quantization for Distributed Deep Learning) aka TernGrad, Stochastic Ternary Gradient Quantization… An unbiased stochastic ternary gradient quantization scheme for distributed synchronous SGD (Wen et al. 2017, Section 3, Equations 4-7) that…	Curated	Algorithms	`AIMech:TernGradTernaryGradientsForDistributedDeepLearning`	4 claims 3 sources
Text Preprocessing Layer A layer that performs text data preprocessing operations.	AIO	Layer	`AIO:TextPreprocessingLayer`	Imported
TextVectorization Layer A text preprocessing layer that maps text features to integer sequences.	AIO	Layer	`AIO:TextVectorizationLayer`	Imported
Theta-IPOD Thresholding-Based Iterative Outlier Detection and Mean-Shift Penalized Regression aka Theta-IPOD, Thresholding-Based Iterative Procedure for Outlier Detection… A thresholding-based iterative outlier detection and robust regression algorithm family ($\Theta$-IPOD, introduced by Yiyuan She and Art B.…	Curated	Algorithms	`AIMech:ThetaIPODThresholdingBasedIterativeOutlierDetectionAndMeanShiftPenalizedRegression`	3 claims 3 sources
Threshold Autoregressive aka TAR A model that allows for different autoregressive processes depending on the regime or state of the time series, enabling the capture of nonl…	AIO	Model	`AIO:ThresholdAutoregressive`	Imported
ThresholdedReLU Layer An activation layer that applies the thresholded rectified linear unit function element-wise.	AIO	Layer	`AIO:ThresholdedReLULayer`	Imported
Tied-LoRA aka Tied Low-Rank Adaptation, Weight-Tied Selective Low-Rank Adaptation… A parameter-efficient fine-tuning algorithm that enhances low-rank adaptation by sharing low-rank projection matrices across transformer lay…	Curated	Algorithms	`AIMech:TiedLoRA`	4 claims 3 sources
Time Series Analysis A machine learning task focused on methods for analyzing time series data to extract meaningful statistics and characteristics.	AIO	MachineLearningTask	`AIO:TimeSeriesAnalysis`	Imported
Time Series Forecasting A machine learning task focused on methods that predict future values based on previously observed values.	AIO	MachineLearningTask	`AIO:TimeSeriesForecasting`	Imported
TimeDistributed Layer A recurrent layer that applies a layer to every temporal slice of an input.	AIO	Layer	`AIO:TimeDistributedLayer`	Imported
TinyBERT (Two-Stage Transformer Distillation for Natural Language Understanding) aka TinyBERT, TinyBERT Transformer Distillation… A two-stage knowledge distillation framework for Transformer language models (Jiao et al., Findings of EMNLP 2020) that transfers knowledge…	Curated	Learning Paradigms	`AIMech:TinyBERTTransformerDistillationForNaturalLanguageUnderstanding`	4 claims 3 sources
TK Transformer-Kernel Neural Re-Ranking Model aka TK Model, Transformer-Kernel Re-Ranking Model… An interpretable, time-budget-constrained neural re-ranking architecture that independently contextualizes query and document sequences by b…	Curated	Architectures	`AIMech:TKTransformerKernelModelForReRanking`	4 claims 3 sources
TKL: Transformer-Kernel Model with Local Self-Attention for Long Document Retrieval aka TKL Long-Document Ranking Model, Transformer-Kernel for Long Text… A long-document neural re-ranking architecture (Hofstätter, Zamani, Mitra, Craswell, & Hanbury, SIGIR 2020) that contextualizes document tok…	Curated	Architectures	`AIMech:TKLTransformerKernelForLongDocuments`	3 claims 3 sources
Tokenization aka Lexical Analysis, Text Segmentation A data preparation that converts a sequence of text into smaller meaningful units called tokens typically words or subwords for the purpose…	AIO	Preprocessing	`AIO:Tokenization`	Imported
TONGA Topmoumoute Online Natural Gradient Optimization aka TONGA, Topmoumoute Online Natural Gradient Algorithm… TONGA (Topmoumoute Online Natural Gradient Algorithm) is an online natural gradient optimization algorithm that approximates the empirical g…	Curated	Algorithms	`AIMech:TongaTopmoumouteOnlineNaturalGradientOptimization`	4 claims 3 sources
Top-K Ranking by Spectral Method and Regularized Maximum Likelihood via Leave-One-Out Analysis aka Leave-One-Out Entrywise Optimal Spectral and Regularized MLE Top-K Ranking, Chen-Fan-Ma-Wang Minimax Top-K BTL Ranking… A unified pairwise-comparison ranking and entrywise $\ell_\infty$ estimation framework (established by Yuxin Chen, Jianqing Fan, Cong Ma, an…	Curated	Mathematical Methods	`AIMech:TopKRankingSpectralAndRegularizedMLEByLeaveOneOutAnalysis`	3 claims 3 sources
Topic-model evocation score aka Top-m evocation metric A topic-model evaluation method that orders judged word pairs by model-derived weights and sums their human evocation ratings over a chosen…	Curated	Evaluation Methods	`AIMech:TopicModelEvocationScore`	2 claims 2 sources
Topical n-gram model aka TNG A topic-conditioned sequence model that chooses whether each word uses a topic-specific unigram distribution or a topic-and-previous-word bi…	Curated	Model Families	`AIMech:TopicalNGramModel`	2 claims 1 source
Topics over Time model aka TOT A topic-model family combining fixed topic-word distributions with topic-specific continuous timestamp densities, so that words and their ob…	Curated	Model Families	`AIMech:TopicsOverTimeModel`	2 claims 1 source
Topographic Independent Component Analysis aka Topographic ICA, TICA A linear latent-component model whose otherwise conditionally independent source components share random scales through fixed overlapping ne…	Curated	Model Families	`AIMech:TopographicICA`	4 claims 1 source
Tractable unnormalized Barber–Agakov bound aka TUBA, TUBA bound A tractable unnormalized Barber–Agakov lower-bound parameterization that uses a real critic and a positive output-dependent normalizer to re…	Curated	Mathematical Methods	`AIMech:TUBABound`	2 claims 2 sources
Training signal annealing aka TSA A supervised-loss scheduling procedure that temporarily excludes labeled examples already predicted with confidence above an increasing thre…	Curated	Algorithms	`AIMech:TrainingSignalAnnealing`	1 claim 3 sources
TrainingStrategy aka Instructional Methods, Learning Techniques A preprocessing used to train machine learning models including techniques such as supervised learning unsupervised learning reinforcement l…	AIO	TrainingStrategy	`AIO:TrainingStrategy`	Imported
Transfer Learning A machine learning task focused on methods that reuse or transfer information from previously learned tasks to facilitate the learning of ne…	AIO	MachineLearningTask	`AIO:TransferLearning`	Imported
Transfer Learning LLM aka Transfer LLM, transfer learning A large language model that leverages knowledge acquired during training on one task to improve performance on different but related tasks f…	AIO	Model	`AIO:TransferLearningLLM`	Imported
Transformer Language Model aka Transformer LM A language model that uses the transformer architecture based on multi-head attention mechanisms allowing it to contextualize tokens within…	AIO	Model	`AIO:TransformerLanguageModel`	Imported
Transformer LLM aka Transformer Large Language Model A transformer language model with large training corpuses and sets of parameters that uses the transformer architecture based on multi-head…	AIO	Model	`AIO:TransformerLLM`	Imported
Transformer Network A deep neural network that utilizes attention mechanisms to weigh the significance of input data.	AIO	Network	`AIO:TransformerNetwork`	Imported
Transforming autoencoder A deterministic neural architecture that learns first-level capsules from images, transformed target images and supplied transformations. Ea…	Curated	Architectures	`AIMech:TransformingAutoencoder`	6 claims 1 source
Tree SHAP A tree-specific algorithm computing Shapley feature attributions through recursive bookkeeping of weighted feature subsets along decision pa…	Curated	Algorithms	`AIMech:TreeSHAP`	2 claims 2 sources
Tree-size estimation by partial backtracking aka Purdom partial-backtracking estimator A randomized backtracking-tree estimator that explores a uniformly selected subset of successors at each visited branching point and uses in…	Curated	Algorithms	`AIMech:PartialBacktrackingTreeEstimation`	5 claims 1 source
Tree-structured Parzen Estimator aka TPE, Tree-structured Parzen Estimator Approach A sequential hyperparameter optimization method that separates observations by a loss quantile, fits tree-structured densities for the bette…	Curated	Algorithms	`AIMech:TreeStructuredParzenEstimator`	1 claim 1 source
TriMap A nonlinear dimensionality-reduction algorithm that selects weighted triplet comparisons from high-dimensional data and optimizes embedding…	Curated	Algorithms	`AIMech:TriMap`	2 claims 2 sources
Triplet Markov chain aka TMC A latent-variable sequence-model family that introduces an auxiliary process so that the joint hidden, auxiliary and observed process is fir…	Curated	Model Families	`AIMech:TripletMarkovChain`	1 claim 1 source
Triplet Markov field aka TMF A latent-variable spatial-model family that introduces an auxiliary field so the complete hidden, auxiliary and observed triplet has a norma…	Curated	Model Families	`AIMech:TripletMarkovField`	1 claim 1 source
True online GTD(lambda) A linear off-policy state-value prediction algorithm that couples two Dutch eligibility traces with an accumulating gradient-correction trac…	Curated	Algorithms	`AIMech:TrueOnlineGTDLambda`	6 claims 1 source
True online Sarsa(lambda) A linear on-policy action-value control algorithm that combines a Dutch eligibility trace with a correction for changing predictions, using…	Curated	Algorithms	`AIMech:TrueOnlineSarsaLambda`	6 claims 2 sources
True online TD(lambda) A linear temporal-difference policy-evaluation algorithm that combines a Dutch eligibility trace with a correction for changing predictions,…	Curated	Algorithms	`AIMech:TrueOnlineTDLambda`	6 claims 2 sources
Truncated Amplitude Flow and Orthogonality-Promoting Initialization for Random Quadratic Equations aka Truncated Amplitude Flow (TAF), Orthogonality-Promoting Initialization and Truncated Generalized Gradient Flow… A two-stage nonconvex-nonsmooth phase retrieval algorithm (introduced by Gang Wang, Georgios B. Giannakis, and Yonina C. Eldar in 2018) that…	Curated	Algorithms	`AIMech:TruncatedAmplitudeFlowAndOrthogonalityPromotingInitializationForQuadraticEquations`	3 claims 3 sources
Truncated Poisson graphical model aka TPGM, Truncated Poisson Markov random field A finite pairwise count graphical model with a fixed upper count limit, factorial base measures and Poisson-kernel full conditionals renorma…	Curated	Model Families	`AIMech:TruncatedPoissonGraphicalModel`	1 claim 2 sources
Truncated Power Method for Sparse Eigenvalue and Sparse PCA aka Truncated Power Method, TPower… Truncated Power Method for Sparse Eigenvalue and Sparse PCA (TPower) is a non-convex iterative hard-thresholding spectral algorithm introduc…	Curated	Algorithms	`AIMech:TruncatedPowerMethodForSparseEigenvalueAndSparsePCA`	3 claims 3 sources
Truncated Wirtinger Flow and Truncated Spectral Initialization for Random Quadratic Systems aka Truncated Wirtinger Flow (TWF), Chen-Candes Truncated Poisson Phase Retrieval… An adaptive nonconvex phase-retrieval and quadratic-sensing algorithm (introduced by Yuxin Chen and Emmanuel J. Candès in 2017) that solves…	Curated	Algorithms	`AIMech:TruncatedWirtingerFlowAndTruncatedSpectralInitializationForQuadraticSystems`	3 claims 3 sources
Trust region policy optimization aka TRPO A policy-optimization method that optimizes a surrogate objective while constraining the change in policy by a trust region based on Kullbac…	Curated	Algorithms	`AIMech:TrustRegionPolicyOptimization`	1 claim 1 source
TSHT Two-Stage Hard Thresholding with Plurality Voting for Invalid Instruments aka TSHT with Plurality Voting, Two-Stage Hard Thresholding with Voting for Invalid Instruments… An instrumental variable causal inference and confidence interval construction method for settings with invalid instruments that first appli…	Curated	Mathematical Methods	`AIMech:TSHTTwoStageHardThresholdingWithPluralityVotingForInvalidInstruments`	4 claims 3 sources
TTQ (Trained Ternary Quantization) aka TTQ, Trained Ternary Quantization TTQ (Trained Ternary Quantization) is a neural network weight quantization method that compresses full-precision weights into 2-bit asymmetr…	Curated	Algorithms	`AIMech:TTQTrainedTernaryQuantization`	4 claims 3 sources
TwinBERT (Distilling Knowledge to Twin-Structured BERT Models for Efficient Retrieval) aka TwinBERT, Twin-Structured BERT for Efficient Retrieval… A twin-structured dual-encoder Transformer architecture and teacher-student knowledge distillation framework for low-latency retrieval and r…	Curated	Architectures	`AIMech:TwinBERTDistillingKnowledgeToTwinStructuredBERTModels`	4 claims 3 sources
Two-stage adaptive-neighborhood sparse-spectrum regression A query-specific sparse-spectrum regression procedure that fits a variational model to Euclidean neighbors, reselects neighbors from the ful…	Curated	Algorithms	`AIMech:TwoStageAdaptiveNeighborhoodSparseSpectrumRegression`	5 claims 1 source
Two-Stage Hard Thresholding with Voting and Plurality Rule for Invalid Instruments aka TSHT, Two-Stage Hard Thresholding with Voting… A causal-effect estimation and confidence-interval construction methodology (introduced by Zijian Guo, Hyunseung Kang, T. Tony Cai, and Dyla…	Curated	Algorithms	`AIMech:TwoStageHardThresholdingWithVotingAndPluralityRuleForInvalidInstruments`	3 claims 3 sources
UDapter Typology-Conditioned Contextual Parameter Adapter aka UDapter, UDapter Contextual Parameter Generator Adapter… A multilingual language-adaptation architecture that freezes a pre-trained multilingual Transformer encoder (mBERT) and generates both layer…	Curated	Architectures	`AIMech:UDapterTypologyConditionedContextualParameterAdapter`	4 claims 3 sources
UMAP aka Uniform Manifold Approximation and Projection, Uniform Manifold Approximation and Projection for Dimension Reduction A nonlinear embedding algorithm that constructs a locally scaled, symmetrized nearest-neighbor similarity graph and places its vertices in a…	Curated	Algorithms	`AIMech:UMAP`	3 claims 3 sources
Unadjusted Langevin algorithm aka ULA An approximate sampling algorithm that discretizes overdamped Langevin dynamics by an explicit gradient drift and Gaussian noise without a M…	Curated	Algorithms	`AIMech:UnadjustedLangevinAlgorithm`	2 claims 2 sources
Uncertainty Bias A selection and sampling bias favoring groups better represented in training data due to less prediction uncertainty.	AIO	Bias	`AIO:UncertaintyBias`	Imported
uniCOIL Unified Contextualized Inverted List Sparse Retrieval aka uniCOIL, Unified Contextualized Inverted List… A learned sparse retrieval architecture that extends Contextualized Inverted List (COIL) by reducing the token representation dimension to d…	Curated	Architectures	`AIMech:uniCOILUnifiedContextualizedInvertedList`	4 claims 3 sources
Unified assumption-lean moving-target linear regression and score bootstrap aka Model-free study of ordinary least squares linear regression (Kuchibhotla, Brown, & Buja 2018), Unified independent non-identically distributed moving-target OLS framework… An assumption-lean statistical estimation and inference methodology for ordinary least squares (OLS) linear regression that starts with the…	Curated	Mathematical Methods	`AIMech:UnifiedAssumptionLeanMovingTargetLinearRegressionAndScoreBootstrap`	4 claims 2 sources
Unified Parametric Theory of Proximal SGD aka Unified (A,B,C,D1,D2,rho) Theory of SGD, ABC-SGD Parametric Framework… A unified parametric convergence analysis framework for composite strongly convex stochastic optimization min_{x in R^d} f(x) + R(x) using p…	Curated	Mathematical Methods	`AIMech:UnifiedSgdParametricRecursionTheory`	4 claims 3 sources
Uniform-in-submodel deterministic linear regression and functional dependence bounds aka Model-Free Uniform-in-Submodel OLS Consistency and Bahadur Linear Representation Bounds, General Linear Regression Map beta_M(Sigma, Gamma) Deterministic Submodel Inequalities… Uniform-in-submodel deterministic linear regression and functional dependence bounds are a model-free high-dimensional statistical methodolo…	Curated	Mathematical Methods	`AIMech:UniformInSubmodelDeterministicLinearRegressionAndFunctionalDependenceBounds`	4 claims 2 sources
Uniformly valid post-model-selection confidence intervals via consistent variance overestimation aka Bachoc-Preinerstorfer-Steinberger uniformly valid post-model-selection confidence intervals, Asymptotically uniformly valid PoSI confidence intervals under model misspecification… A general post-model-selection inference framework and family of confidence intervals CI^{(j)}_{1-alpha, M_hat_n}(y) = theta_hat^{(j)}_{M_ha…	Curated	Mathematical Methods	`AIMech:UniformlyValidPostModelSelectionConfidenceIntervals`	4 claims 3 sources
UniPELT aka Unified Parameter-Efficient Language Model Tuning, UniPELT (APL)… A unified parameter-efficient language model tuning architecture that incorporates multiple heterogeneous parameter-efficient tuning methods…	Curated	Architectures	`AIMech:UniPELT`	3 claims 3 sources
UnitNormalization Layer A recurrent layer that normalizes a batch of inputs so that each input in the batch has a L2 norm equal to 1.	AIO	Layer	`AIO:UnitNormalizationLayer`	Imported
Univariate marginal distribution algorithm The original unsmoothed binary population optimizer that selects a nonempty set of evaluated bit strings, replaces each coordinate probabili…	Curated	Algorithms	`AIMech:UnivariateMarginalDistributionAlgorithm`	6 claims 2 sources
Universal inference split likelihood ratio test aka Split Likelihood Ratio Test, Split LRT… A regularity-free, finite-sample statistical hypothesis testing and confidence set construction framework (Wasserman, Ramdas, & Balakrishnan…	Curated	Mathematical Methods	`AIMech:UniversalInferenceSplitLikelihoodRatioTest`	4 claims 3 sources
Unsupervised Biclustering aka Unsupervised Block Clustering, Unsupervised Co-clustering… A biclustering task focused on methods that simultaneously cluster the rows and columns of an unlabeled input matrix to identify submatrices…	AIO	MachineLearningTask	`AIO:UnsupervisedBiclustering`	Imported
Unsupervised Clustering aka Unsupervised Cluster Analysis A clustering focused on methods that group a set of unlabeled objects such that objects in the same group are more similar to each other tha…	AIO	MachineLearningTask	`AIO:UnsupervisedClustering`	Imported
Unsupervised Data Augmentation aka UDA A semi-supervised classifier-training procedure that combines labeled prediction loss with consistency between fixed current-model predictio…	Curated	Algorithms	`AIMech:UnsupervisedDataAugmentation`	1 claim 5 sources
Unsupervised Learning A machine learning task focused on algorithms that learn patterns from unlabeled data.	AIO	MachineLearningTask	`AIO:UnsupervisedLearning`	Imported
Unsupervised LLM aka Unsupervised Large Language Model, self-supervised A large language model that is trained solely on unlabeled data using self-supervised objectives like masked language modeling without any s…	AIO	Model	`AIO:UnsupervisedLLM`	Imported
Unsupervised Pretrained Network aka UPN A network that initializes a discriminative neural net from one trained using an unsupervised criterion.	AIO	Network	`AIO:UnsupervisedPretrainedNetwork`	Imported
Unweighted Multiview Convex Mixture Clustering aka Multiview Convex Mixture Model Clustering, Convex Mixture Models for Multi-view Clustering A multiview exemplar-clustering procedure that fits a single vector of exemplar weights by minimizing the equally weighted sum of fixed-comp…	Curated	Algorithms	`AIMech:UnweightedMultiviewConvexMixtureClustering`	3 claims 1 source
UPR (Unsupervised Passage Re-ranking with Zero-Shot Question Generation) aka Unsupervised Passage Re-ranker, Unsupervised Passage Re-ranking… An unsupervised zero-shot passage re-ranking algorithm for information retrieval and open-domain question answering that re-orders top-K can…	Curated	Algorithms	`AIMech:UPRUnsupervisedPassageRerankingWithQuestionGeneration`	3 claims 3 sources
UpSampling1D Layer A reshaping layer that upsamples the input by repeating each temporal step size times along the time axis.	AIO	Layer	`AIO:UpSampling1DLayer`	Imported
UpSampling2D Layer A layer that upsamples the input by repeating each row and column size times.	AIO	Layer	`AIO:UpSampling2DLayer`	Imported
UpSampling3D Layer A layer that upsamples the input by repeating each depth, height and width size times.	AIO	Layer	`AIO:UpSampling3DLayer`	Imported
Upward-downward nested antithetic mixture A finite conditional Markov update that chooses with equal probability between complete upward and downward nested antithetic modification k…	Curated	Algorithms	`AIMech:UpwardDownwardNestedAntitheticMixture`	6 claims 1 source
Upward-downward shifted tower mixture A finite conditional Markov update that equally mixes maximum-shift tower kernels built from paired upward and downward cyclic state orders,…	Curated	Algorithms	`AIMech:UpwardDownwardShiftedTowerMixture`	6 claims 1 source
Usage-based TD(lambda) An on-policy linear state-value prediction algorithm that combines ordinary accumulating TD eligibility traces with componentwise step sizes…	Curated	Algorithms	`AIMech:UsageBasedTDLambda`	6 claims 1 source
Usage-based true online TD(lambda) An on-policy linear state-value prediction algorithm that combines componentwise inverse feature-usage step sizes with a component-scaled Du…	Curated	Algorithms	`AIMech:UsageBasedTrueOnlineTDLambda`	6 claims 1 source
Use And Interpretation Bias aka Interpretive Bias A computational bias characterized by inappropriately analyzing ambiguous stimuli scenarios and events.	AIO	Bias	`AIO:UseAndInterpretationBias`	Imported
User Interaction Bias An individual bias arising when a user imposes their own biases during interaction with data output results etc.	AIO	Bias	`AIO:UserInteractionBias`	Imported
Value-based abstraction functions for abstraction sampling aka Value-based abstraction sampling A family of graphical-model sampling abstractions that assigns a positive scalar value to each current search node and partitions nodes in v…	Curated	Mathematical Methods	`AIMech:ValueBasedAbstractionSampling`	6 claims 1 source
Vanilla sequence beam decoding aka Vanilla beam decoding A layer-based sequence beam decoder in which completed and unfinished hypotheses compete for the same k beam slots: finished hypotheses are…	Curated	Algorithms	`AIMech:VanillaSequenceBeamDecoding`	2 claims 2 sources
Vanishing gradient regularization A recurrent-network training regularization procedure that softly penalizes deviations from unit norm gain when a local recurrent Jacobian t…	Curated	Algorithms	`AIMech:VanishingGradientRegularization`	6 claims 3 sources
Variable neighborhood search A local-search metaheuristic that repeatedly perturbs an incumbent through an indexed collection of neighborhoods, locally optimizes the per…	Curated	Algorithms	`AIMech:VariableNeighborhoodSearch`	5 claims 1 source
Variance-Reduced Stochastic PCA and SVD with Exponential Convergence (VR-PCA) aka Shamir VR-PCA Algorithm, Variance-Reduced Oja Iteration for Principal Component Analysis… Variance-Reduced Stochastic PCA and SVD with Exponential Convergence (VR-PCA) is an epoch-based stochastic spectral optimization algorithm i…	Curated	Algorithms	`AIMech:VarianceReducedStochasticPCAWithExponentialConvergence`	3 claims 3 sources
Variational Auto Encoder aka VAE An autoencoder network that imposes a probabilistic structure on the latent space for unsupervised learning.	AIO	Network	`AIO:VariationalAutoEncoder`	Imported
Variational Expectation Maximization aka Variational EM, VEM (variational expectation maximization) A latent-variable model-fitting procedure that alternates optimization of a posterior approximation within a specified restricted family and…	Curated	Algorithms	`AIMech:VariationalExpectationMaximization`	4 claims 1 source
Variational Fair Autoencoder aka VFAE A variational autoencoder architecture for learning representations with reduced sensitive or nuisance information, combining sensitive-vari…	Curated	Architectures	`AIMech:VariationalFairAutoencoder`	1 claim 1 source
Variational information maximization IM algorithm aka IM algorithm, IM algorithm (Barber and Agakov) An alternating optimization procedure that adjusts a noisy encoder and a variational decoder to increase the Barber–Agakov lower bound on tr…	Curated	Algorithms	`AIMech:VariationalInformationMaximizationIMAlgorithm`	1 claim 1 source
Variational message passing aka VMP A variational inference algorithm that organizes conjugate-exponential coordinate updates as local messages carrying expected sufficient sta…	Curated	Algorithms	`AIMech:VariationalMessagePassing`	7 claims 1 source
Variational sparse-spectrum Gaussian-process inference aka VSSGP The Gal–Turner finite spectral regression inference procedure that factorizes spectral parameters from output coefficients, analytically opt…	Curated	Algorithms	`AIMech:VariationalSparseSpectrumGaussianProcessInference`	5 claims 3 sources
Vector Autoregression aka VAR A model that captures the linear interdependencies among multiple time series, where each variable is modeled as a linear function of its ow…	AIO	Model	`AIO:VectorAutoregression`	Imported
Vector-based Random Matrix Adaptation (VeRA) aka VeRA, Vector-based Random Matrix Adaptation… Vector-based Random Matrix Adaptation (VeRA) is a parameter-efficient fine-tuning (PEFT) method that reparameterizes the low-rank weight upd…	Curated	Algorithms	`AIMech:VeraVectorBasedRandomMatrixAdaptation`	4 claims 3 sources
Vertex Attention Interaction Network aka VAIN A neural architecture for multi-agent predictive modeling that encodes each agent separately, aggregates communication vectors using learned…	Curated	Architectures	`AIMech:VertexAttentionInteractionNetwork`	6 claims 1 source
Vicinal risk minimization aka VRM A risk-minimization principle that chooses a predictor from a specified function class by minimizing expected loss under an estimated distri…	Curated	Mathematical Methods	`AIMech:VicinalRiskMinimization`	1 claim 1 source
VICReg aka Variance-invariance-covariance regularization A self-supervised joint-embedding procedure that combines a paired-view invariance loss with separate per-branch penalties for insufficient…	Curated	Algorithms	`AIMech:VICReg`	1 claim 4 sources
Virtual adversarial training aka VAT A prediction-smoothing regularization procedure that trains a model to preserve its current output distribution under approximately worst-ca…	Curated	Algorithms	`AIMech:VirtualAdversarialTraining`	1 claim 4 sources
Vocabulary Reduction aka Lexical Simplification, Lexicon Pruning… A data preparation that limits the number of unique tokens in a language model's vocabulary by merging or eliminating less frequent tokens t…	AIO	Preprocessing	`AIO:VocabularyReduction`	Imported
Volume Sampling for Matrix Approximation and Projective Clustering aka Deshpande-Rademacher-Vempala-Wang Simplex Volume Sampling, k-Simplex Volume-Squared Row Subset Selection… Volume Sampling for Matrix Approximation and Projective Clustering is a joint geometric row-subset sampling principle and adaptive low-rank…	Curated	Mathematical Methods	`AIMech:VolumeSamplingForMatrixApproximationAndProjectiveClustering`	3 claims 3 sources
Vote-k Selective Annotation for In-Context Learning aka Vote-k Selective Annotation, Vote-k Graph-Based Selective Annotation… A graph-based selective annotation algorithm for few-shot in-context learning that constructs a directed k-nearest-neighbor graph over dense…	Curated	Algorithms	`AIMech:VoteKSelectiveAnnotationForInContextLearning`	4 claims 3 sources
Voting classifier aka Hard voting, Soft voting A classifier combining base predictions through class votes or aggregated class probabilities.	Curated	Model Families	`AIMech:VotingClassifier`	1 claim 1 source
VR-DIANA and SVRG-DIANA (Variance-Reduced Distributed Learning with Gradient Quantization) aka VR-DIANA, Variance-Reduced DIANA… VR-DIANA and SVRG-DIANA are doubly variance-reduced distributed optimization algorithms for solving min_{x in R^d} f(x) = (1/n) sum_{i=1}^n…	Curated	Algorithms	`AIMech:VrDianaAndSvrgDianaVarianceReducedQuantizedDistributedOptimization`	4 claims 3 sources
Wake-sleep algorithm aka Wake-sleep An alternating learning procedure that trains a generative network from observed data and recognition-sampled hidden states during wake, and…	Curated	Algorithms	`AIMech:WakeSleepAlgorithm`	1 claim 3 sources
WalkSAT aka WalkSAT/SKC, SKC WalkSAT A clause-focused SAT local-search algorithm, in its classical SKC formulation, that first selects an unsatisfied clause, prioritizes a varia…	Curated	Algorithms	`AIMech:WalkSAT`	1 claim 2 sources
Ward minimum-variance clustering aka Ward hierarchical clustering, Ward minimum-variance method… An agglomerative clustering algorithm for Euclidean observations that starts from singletons and repeatedly merges the pair causing the smal…	Curated	Algorithms	`AIMech:WardMinimumVarianceClustering`	6 claims 2 sources
WARP (Word-level Adversarial ReProgramming) aka WARP, WARP_init… A parameter-efficient transfer learning method for frozen masked language models that inserts K special prompt tokens [P_1], ..., [P_K] and…	Curated	Algorithms	`AIMech:WARPWordLevelAdversarialReProgramming`	4 claims 3 sources
Watkins hard-cut multistep Q-learning The original hard-cut multistep Q-learning construction that estimates action returns using maximum-value bootstraps and continuation throug…	Curated	Algorithms	`AIMech:WatkinsHardCutMultistepQLearning`	5 claims 1 source
Wavelet-domain hidden Markov model aka Wavelet hidden Markov model, Wavelet-domain HMM A statistical wavelet-coefficient model family using latent mixture states to represent coefficient distributions and Markov dependencies am…	Curated	Model Families	`AIMech:WaveletHiddenMarkovModel`	1 claim 1 source
Weight-Decomposed Low-Rank Adaptation (DoRA) aka DoRA, Weight-Decomposed Low-Rank Adaptation… Weight-Decomposed Low-Rank Adaptation (DoRA) is a parameter-efficient fine-tuning (PEFT) method that decomposes a pretrained weight matrix W…	Curated	Algorithms	`AIMech:DoraWeightDecomposedLowRankAdaptation`	4 claims 3 sources
Weighted A-star search aka Weighted A, WA A heuristic best-first search algorithm that orders open nodes by g+w h using a fixed finite weight w greater than one, where g is path cost…	Curated	Algorithms	`AIMech:WeightedAStar`	3 claims 3 sources
Weighted Layer A layer of values to be applied to other cells or neurons in a network.	AIO	Layer	`AIO:WeightedLayer`	Imported
Weighted Multiview Convex Mixture Clustering aka Weighted Multiview CMM Clustering A multiview exemplar-clustering procedure that learns shared exemplar weights and view weights through outer view-responsibility updates and…	Curated	Algorithms	`AIMech:WeightedMultiviewConvexMixtureClustering`	5 claims 1 source
Weighted Multiview Spectral Clustering aka MVSpec, Tzortzis-Likas Multiview Spectral Clustering A multiview clustering algorithm that alternates a leading-eigenspace relaxation of within-cluster variance with simplex weights for a power…	Curated	Algorithms	`AIMech:WeightedMultiviewSpectralClustering`	6 claims 1 source
Whitening mean squared error aka W-MSE, Whitening MSE A self-supervised representation-learning procedure that differentiably whitens projected image-view embeddings and minimizes the average sq…	Curated	Algorithms	`AIMech:WhiteningMSE`	1 claim 5 sources
Wiener model A real-valued, single-input single-output, discrete-time deterministic nonlinear dynamical model family formed by a causal linear time-invar…	Curated	Model Families	`AIMech:WienerModel`	4 claims 1 source
Wiener–Hammerstein model A real-valued, single-input single-output, discrete-time deterministic dynamical model family formed by a causal linear time-invariant block…	Curated	Model Families	`AIMech:WienerHammersteinModel`	4 claims 1 source
Wirtinger Flow Phase Retrieval and Spectral Initialization aka Wirtinger Flow (WF) Algorithm for Phase Retrieval, Candes-Li-Soltanolkotabi Spectral Initialization and Wirtinger Gradient Descent… A two-stage nonconvex optimization algorithm (introduced by Emmanuel J. Candès, Xiaodong Li, and Mahdi Soltanolkotabi in 2015) for recoverin…	Curated	Algorithms	`AIMech:WirtingerFlowPhaseRetrievalAndSpectralInitialization`	3 claims 3 sources
WIS-GTD(lambda) A linear off-policy state-value prediction algorithm that combines an importance-weighted accumulating eligibility trace and an auxiliary GT…	Curated	Algorithms	`AIMech:WISGTDLambda`	6 claims 1 source
WIS-TD(lambda) A linear off-policy state-value prediction algorithm that combines component step sizes from feature usage, a scaled Dutch eligibility trace…	Curated	Algorithms	`AIMech:WISTDLambda`	6 claims 1 source
WIS-TO-GTD(lambda) A linear off-policy state-value prediction adaptation of true online GTD(lambda) that derives componentwise main-weight step sizes from feat…	Curated	Algorithms	`AIMech:WISTrueOnlineGTDLambda`	6 claims 3 sources
WNGrad aka Weight-Normalization Inspired Adaptive Learning Rate Gradient Descent, Square-Root-Free Reciprocal Step-Size Update Optimization… A weight-normalization-inspired adaptive step-size gradient descent algorithm that maintains an inverse learning-rate scalar b_k > 0 (global…	Curated	Algorithms	`AIMech:WNGrad`	4 claims 3 sources
word2vec aka W2V A machine learning task that generates distributed representations of words by training a shallow neural network model, which aims to predic…	AIO	MachineLearningTask	`AIO:word2vec`	Imported
word2vec-CBOW aka W2V-CBOW, CBOW A word2vec that predicts the current word from a window of surrounding context words, ignoring the order of context words.	AIO	MachineLearningTask	`AIO:word2vecCBOW`	Imported
word2vec-SkipGram aka W2V-SkipGram, SkipGram A word2vec that predicts surrounding context words from the current word, giving more weight to nearby context words than distant ones.	AIO	MachineLearningTask	`AIO:word2vecSkipGram`	Imported
Worst-Case Proximal Denoising Normalized Mean-Squared Error and Subdifferential Mean-Squared Distance aka Proximal Denoising Worst-Case NMSE and Subdifferential Distance, Oymak-Hassibi Sharp MSE Bounds for Proximal Denoising… Worst-Case Proximal Denoising Normalized Mean-Squared Error and Subdifferential Mean-Squared Distance is a convex-geometric and statistical…	Curated	Mathematical Methods	`AIMech:WorstCaseProximalDenoisingNMSEAndSubdifferentialMeanSquaredDistance`	3 claims 3 sources
Wrapper Layer A layer that augment the functionality of another layer.	AIO	Layer	`AIO:WrapperLayer`	Imported
YellowFin Automatic Momentum and Learning Rate Tuner aka YellowFin, YellowFin Optimizer… An automatic hyperparameter tuning algorithm for Polyak heavy-ball momentum stochastic gradient descent (x_{t+1} = x_t - alpha_t grad f_{S_t…	Curated	Algorithms	`AIMech:YellowFinAutomaticMomentumAndLearningRateTuner`	4 claims 3 sources
Zeno Suspicion-Based Fault-Tolerant Distributed Stochastic Gradient Descent aka Zeno, Zeno Distributed SGD… A Byzantine-tolerant synchronous distributed stochastic gradient descent algorithm in which the parameter server samples a small validation…	Curated	Algorithms	`AIMech:ZenoSuspicionBasedFaultTolerantDistributedStochasticGradientDescent`	3 claims 3 sources
Zeno++ Robust Fully Asynchronous Stochastic Gradient Descent aka Zeno++, Zeno++ Byzantine-Tolerant Fully Asynchronous SGD… A Byzantine-tolerant fully asynchronous stochastic gradient descent algorithm for parameter-server architectures with anonymous workers, unb…	Curated	Algorithms	`AIMech:ZenoPlusPlusRobustFullyAsynchronousStochasticGradientDescent`	4 claims 3 sources
ZeRO-Infinity aka Zero Redundancy Optimizer Infinity, ZeRO-Infinity NVMe-CPU-GPU Offload… A heterogeneous distributed deep learning training system and algorithm built on ZeRO Stage-3 that partitions all model states (parameters,…	Curated	Algorithms	`AIMech:ZeROInfinityHeterogeneousExtremeScaleTraining`	4 claims 3 sources
ZeRO-Offload aka Zero Redundancy Optimizer Offload, ZeRO-Offload Heterogeneous GPU-CPU Training… A heterogeneous GPU-CPU deep learning training algorithm for mixed-precision Adam optimization that partitions the directed cyclic training…	Curated	Algorithms	`AIMech:ZeROOffloadHeterogeneousLargeModelTraining`	4 claims 3 sources
Zero-self downward nested antithetic modification A finite conditional sampling construction that follows downward nested antithetic modification and replaces stages retaining avoidable self…	Curated	Algorithms	`AIMech:ZeroSelfDownwardNestedAntitheticModification`	6 claims 1 source
Zero-self flattened slice sampling A finite categorical conditional-update algorithm that flattens probability bars and relocates a qualifying blocker before the maximum-proba…	Curated	Algorithms	`AIMech:ZeroSelfFlattenedSliceSampling`	6 claims 1 source
Zero-shot Learning aka ZSL A deep neural network that predicts classes at test time from classes not observed during training.	AIO	Network	`AIO:ZeroshotLearning`	Imported
Zero-Shot Learning LLM aka Zero-Shot LLM, zero-shot learning A large language model which performs tasks or understands concepts it has not explicitly been trained on, demonstrating a high degree of ge…	AIO	Model	`AIO:ZeroShotLearningLLM`	Imported
ZeroPadding1D Layer A reshaping layer that zero-pads the input along the time axis.	AIO	Layer	`AIO:ZeroPadding1DLayer`	Imported
ZeroPadding2D Layer A reshaping layer that zero-pads the input along the height and width dimensions.	AIO	Layer	`AIO:ZeroPadding2DLayer`	Imported
ZeroPadding3D Layer A reshaping layer that zero-pads the input along the depth, height and width dimensions.	AIO	Layer	`AIO:ZeroPadding3DLayer`	Imported
ZeroSARAH and D-ZeroSARAH Variance-Reduced Nonconvex Optimization without Full Gradient Computations aka ZeroSARAH, D-ZeroSARAH… A family of single-loop variance-reduced stochastic optimization algorithms for nonconvex finite-sum minimization f(x) = (1/n) sum_{i=1}^n f…	Curated	Algorithms	`AIMech:ZeroSarahAndDZeroSarahVarianceReducedNonconvexOptimizationWithoutFullGradientComputations`	4 claims 3 sources
Zeta merging An agglomerative graph-clustering algorithm that selects the pair with the largest sum of conditional increases in average log-diagonal reso…	Curated	Algorithms	`AIMech:ZetaMerging`	2 claims 1 source
Zhou first-passage attractor community detection aka Zhou local and global attractor communities A graph community-detection algorithm that forms local or global groups as the minimal nonempty sets closed under a first-passage-time attra…	Curated	Algorithms	`AIMech:ZhouAttractorCommunityDetection`	6 claims 1 source
Zhou random-walk distance-profile dissimilarity aka Zhou neighbor dissimilarity index A pairwise graph dissimilarity that compares the mean first-passage-time profiles of two adjacent vertices by taking the Euclidean norm of t…	Curated	Mathematical Methods	`AIMech:ZhouRandomWalkDissimilarity`	6 claims 2 sources
Zoneout A recurrent-network regularization procedure that randomly preserves selected state components at their previous values instead of applying…	Curated	Algorithms	`AIMech:Zoneout`	1 claim 1 source