AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Solving stochastic weak Minty variational inequalities without increasing batch size

Thomas Pethick, Olivier Fercoq, Puya Latafat, Panagiotis Patrinos, Volkan Cevher

ICLR 2023 · Optimization › Nonconvex and smooth optimization · approach: Extragradient for variational inequalities · 1 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
add a bias-correction term to stochastic extragradient+ (ablation)SEG+ · Unconstrained weak MVI exampleconvergence to solutionImproved
add a bias-correction term to projected stochastic extragradient+ (ablation)Projected SEG+ variant · Constrained minimax exampleconvergence to solutionImproved
use stochastic SEG+ without the bias-correction term (ablation)SEG+ · Unconstrained weak MVI exampleconvergence to solutionHurt
use a projected SEG+ variant without the bias-correction term (ablation)Projected SEG+ variant · Constrained minimax exampleconvergence to solutionHurt
use the compared methods with a non-diminishing second stepsize rather than bias-corrected updatesSEG+ comparison methods · Unconstrained and constrained examplesconvergence to solutionHurt

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