AI Paper Atlas

Research map / Optimization / Optimizers

Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach

Yi Feng, Weiming Ou, Xiao Wang

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 smaller first-order momentum beta in Adam-DA (ablation)Adam-DA · quadratic zero-sum test functions (local convergence)range of step sizes with local convergenceImproved
use larger first-order momentum beta in Adam for minimization (ablation)Adam (minimization) · quadratic test functionrange of step sizes with local convergenceImproved
tune beta, rho, epsilon or step size h for Adam-DA on bilinear gamesAdam-DA · bilinear games x^T A yconvergenceNo clear effect
use smaller beta in Adam-DA GAN training (ablation)Adam-DA · GAN training on CIFAR-10 and STL-10, ResNet and CNNcumulative average gradient L1 normImproved
use larger second-order momentum rho in Adam-DA GAN training (ablation)Adam-DA · GAN training on CIFAR-10 and STL-10, ResNet and CNNcumulative average gradient L1 normImproved
lower gradient norm via smaller beta and larger rho (ablation)Adam-DA GAN training · CIFAR-10 and STL-10Inception ScoreImproved

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