Research map / Optimization / Nonconvex and smooth optimization
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Adapt the extrapolation stepsize using local curvature and backtracking | CurvatureEG+ · GlobalForsaken (deterministic, ρ = -1/(3L)) | convergence to stationary point | Helped |
| Use a fixed second stepsize of 1/2 instead of adapting it (ablation) | CEG+ · GlobalForsaken (deterministic, ρ = -1/(3L)) | convergence to stationary point | Hurt |
| Use a fixed second stepsize of 1 instead of adapting it (ablation) | CEG · GlobalForsaken (deterministic, ρ = -1/(3L)) | convergence to stationary point | Hurt |
| Keep the extrapolation stepsize fixed and decrease the other stepsize (ablation) | SEG+ · Nonconvex-nonconcave minimax example (stochastic) | escape from attracting limit cycle | Helped |
| Diminish both stepsizes (ablation) | SEG · Nonconvex-nonconcave minimax example (stochastic) | convergence to stationary point | Hurt |
| Choose the fixed second stepsize below 1/3 (ablation) | CEG+ · GlobalForsaken (deterministic, ρ = -1/(3L)) | convergence to stationary point | Helped |
| Use a fixed extrapolation stepsize of 1/L (ablation) | CEG+ · PolarGame (a = 1) | convergence to stationary point | Hurt |
Closest papers by meaning
- Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity (ICML 2024 · similarity 0.88)
- Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion (ICML 2024 · similarity 0.87)
- Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization (NeurIPS 2024 · similarity 0.87)
- Two-timescale Extragradient for Finding Local Minimax Points (ICLR 2024 · similarity 0.87)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · similarity 0.87)
- Semi-infinite Nonconvex Constrained Min-Max Optimization (NeurIPS 2025 · similarity 0.87)
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.