Research map / Optimization / Nonconvex and smooth optimization
The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
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 |
|---|---|---|---|
| use OGDA instead of GDA | 2D polynomial example · critical point (0, 0), GDA-unstable but OGDA-stable | probability of convergence (%): 0% -> 25.8% | Helped |
| use OGDA instead of GDA | higher-dimensional planted local min-max · 5+5-dim, 10000 random inits | fraction converging to local min-max (%): 79.3% -> 87% | Helped |
| use OGDA instead of GDA | 2D polynomial example · critical point (1, 0), a local min-max | probability of convergence (%): 78% -> 35.4% | Hurt |
| use OGDA instead of GDA | 2D polynomial example · fraction of initializations that do not converge | non-convergence rate: 3% -> 9.8% | Hurt |
Closest papers by meaning
- On Convergence of Gradient Descent Ascent: A Tight Local Analysis (ICML 2022 · similarity 0.91)
- Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent (NeurIPS 2021 · similarity 0.90)
- Stability and Generalization of Stochastic Gradient Methods for Minimax Problems (ICML 2021 · similarity 0.90)
- Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems (NeurIPS 2022 · similarity 0.90)
- Fundamental Benefit of Alternating Updates in Minimax Optimization (ICML 2024 · similarity 0.89)
- Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics (NeurIPS 2025 · similarity 0.89)
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.