method · first seen 6 Oct 2026
Adam
Also: Adam optimizer, Adaptive Moment Estimation
Adaptive gradient optimizer using per-coordinate first and second moment estimates.
Mentions per week
PapersCodeDiscussion
Rank 168 on 10 Nov 2026 · 17 mentions in 28 days · 15 independent groups · papers · first seen 5 weeks ago · acceleration +1.37
Earliest sources
- Early Memory Selection for Balanced AdamPapers · 6 Oct 2026 · Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre, Manuel F.…
- A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never SpeaksPapers · 7 Oct 2026 · Jonghyun Han, Younghoon Song, Jongyoul Park
- From Geometry to Generalization: Why Row Normalization Can Beat Adam and MuonPapers · 8 Oct 2026 · Jihwan Kim, Dogyoon Song, Chulhee Yun
- Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature ModelsPapers · 9 Oct 2026 · Ran Tian, Courtney Paquette
- Matched Specialization, Different Adaptation: Second-Moment Structure in Shared RepresentationsPapers · 11 Oct 2026 · Toru Takahashi
- Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy ControllerPapers · 13 Oct 2026 · Sagi Habani, Yehonathan Refael, Ofir Lindenbaum
Latest sources
- Grokking Can Be Steered: Selecting Desirable Solutions By Choice Of Learning RulePapers · 14 Nov 2026 · Pascal Sager, Benjamin Grewe, Pau Vilimelis Aceituno, Thilo Stadelmann
- On the Global Convergence of Stochastic Adam for Physics-Informed Neural NetworksPapers · 9 Nov 2026 · Yihang Gao
- Variance-Reduced Stochastic Hessian-Driven Nesterov Acceleration with Adam-Style PreconditioningPapers · 8 Nov 2026 · Yaxin Yu, Long Chen, Minfu Feng
- Full Fine-Tuning is not the Problem: Why Adam Fails and SGD Succeeds in Few-Shot CLIP AdaptationPapers · 8 Nov 2026 · Nairouz Mrabah, Ismail Ben Ayed, Eric Granger
- Coordinatewise Epsilon for Adam under Heavy-Tailed NoisePapers · 6 Nov 2026 · Jeonseong Kim, Chenglin Fan
- Task-Contribution Dynamics of Adam in Physics-Informed Neural Networks: Slow-Manifold Analysis and Gradient ModulationPapers · 6 Nov 2026 · Enzhan Zheng, Xiaoliang Song
- ZEMA: confidence-calibrated signed descent with only one statePapers · 3 Nov 2026 · Ali Dadsetan, Domenic Rosati, Frank Rudzicz
- On the Convergence of Vanilla Adam under Heavy-Tailed Noise and Index SamplingPapers · 2 Nov 2026 · Kanata Oowada, Hideaki Iiduka
- Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate SchedulePapers · 1 Nov 2026 · Eitan Gronich, Gal Vardi
- A Self-Generated Floor on Adam's $\varepsilon$: Evidence from Power-Law Matrix SensingPapers · 1 Nov 2026 · Lngel Kyo
- Adaptive Optimizers Can Get a Policy Ranking Wrong: Momentum, Dependent Data, and a Two-Run RemedyPapers · 31 Oct 2026 · Sunyoung An, Xiaoming Huo
- Guarded Compression of Adam Optimizer State with Shared-Gradient BoundsPapers · 31 Oct 2026 · Annan Zhang, Shengjie Song, Wenshuai Yao, Lihao Zhang, Tianmiao