AdamNC
Algorithms AIMech:AdamNC DRAFT
An Adam-family optimization method that uses time-dependent first- and second-moment decay schedules.
Identity Notes & Concept Scope
AdamNC changes the moment schedules rather than taking AMSGrad's historical maximum. The named method is distinct from an arbitrary claim that any changing Adam hyperparameters ensures convergence.
Claims & Grounded Evidence
1 Claim
Mechanism
#update-rule
Both moment accumulators use iteration-indexed decay coefficients; the original method scales the first-moment step by the square root of the second moment and projects it onto the feasible set.
⚠️ Curated Limitations & Negative Results
- The paper's guarantees require additional conditions on schedules, gradients and the feasible region; no guarantee is asserted for arbitrary schedules or nonconvex training.
- No performance comparison or experimental replication is curated.
Artificial Intelligence Ontology (AIO) Grounding
Mapped AIO Classes
| AIO Target Class | Mapping Relation | Mapping Rationale |
|---|---|---|
AIO:TrainingStrategy
TrainingStrategy
|
related_match | An optimizer can implement parameter fitting, but the pinned TrainingStrategy definition uses a preprocessing genus; no equivalence or subclass relationship is asserted. |
Evidence Sources & Primary Literature
1 Source| Source ID | Publication / Document | Type / Access | Reference & Checksum |
|---|---|---|---|
original-paper
|
Sashank J. Reddi, Satyen Kale, Sanjiv Kumar
|
primary paper
full_text
|
ID: arXiv:1904.09237v1
sha256:75a949b0751e…
|
Curation Provenance
Curator: Codex
Method: ai_assisted
Model: GPT-6
Created: 2026-10-11T03:33:00Z
Updated: 2026-10-11T03:33:00Z
Source File:
data/curated/AdamNC.yaml