AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems

Sucheol Lee, Donghwan Kim

NeurIPS 2021 · Optimization › Nonconvex and smooth optimization · approach: Gradient descent ascent for minimax · 6 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 FEG instead of EAG-C for monotone operatorsextragradient with anchoring · Convex-concave monotonerate-bound constant: 260 -> 4Improved
Use FEG instead of EAG-V for monotone operatorsextragradient with anchoring · Convex-concave monotonerate-bound constant: 27 -> 4Improved
Use FEG instead of EG+ under negative comonotonicityEG+ · Negative comonotonerate on squared gradient norm and rho regionImproved
Use FEG instead of explicit Halpern iteration for cocoercive operators, per iterationHalpern iteration · Cocoerciverate boundMixed
Apply EG+, EAG, Halpern (convex-concave guarantees) to a nonconvex-nonconcave quadraticEG+, EAG-C, EAG-V, Halpern · Toy quadratic, rho=-1/(3L)convergenceHurt

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