AI Paper Atlas

Research map / Optimization / Optimizers

Towards Understanding Adam Convergence on Highly Degenerate Polynomials

Zhiwei Bai, Jiajie Zhao, Zhangchen Zhou, Zhi-Qin John Xu, Yaoyu Zhang

ICML 2026 · Optimization › Optimizers · approach: Adam convergence and adaptive learning rates · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Adam with beta2 > critical value instead of GD or Momentum on degenerate lossGD and Momentum · L(x)=x^k/k, k>=4convergence rate: sublinear power-law t^(-1/(k-2)) -> linearImproved
increase degeneracy from k=2 to k>2Adam · L(x)=x^k/kstability: k=2 loss spikes -> k>2 stable exponential convergenceImproved
require beta1 < beta2^(k/(2(k-2))) (k=4: beta1 < beta2) (ablation)Adam · L(x)=x^4/4 phase diagramconvergence: beta2^1.0 < beta1 < beta2^0.75 gives spikesImproved
raise beta1 above beta2^(0.75) (k=4) (ablation)Adam · L(x)=x^4/4 phase diagramfinal loss: beta1 > beta2^0.75 gives SignGD-like oscillationHurt
increase degeneracy order k above 4Adam · stability regionstable region size: k=4 stability guarantees k>4Improved
keep beta2 above (k-2)/k)^(2(k-2)) for RMSProp (ablation)RMSProp · L(x)=x^4/4stability: beta2 > 0.0625Improved
replace ReLU with softmax in MLPsGD vs Adam · MLP trainingGD speed relative to AdamHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy