AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax Optimization

Mansi Rankawat, Michael Muehlebach, Simon Lacoste-Julien, Damien Scieur

ICML 2026 · Optimization › Nonconvex and smooth optimization · approach: Extragradient for variational inequalities

Read the paper

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 TALDA instead of AGDA, weakly coupled regime (kappa_xy=2, kappa=10)AGDA · Synthetic quadratic minimax (dx=50, dy=100)Lyapunov convergence rateImproved
use TALDA instead of AGDA, strongly coupled regime (kappa_xy=20, kappa=10)AGDA · Synthetic quadratic minimax (dx=50, dy=100)Lyapunov convergence rateImproved
use TALDA instead of AGDA with theoretical, adaptive and fine-tuned step sizesAGDA · Robust least squaresLyapunov function vs gradient evaluationsImproved
use adaptive step-size estimation instead of theoretical constants (ablation)TALDA · Robust least squaresconvergenceNo clear effect

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