Research map / Optimization / Nonconvex and smooth optimization
Optimal Epoch Stochastic Gradient Descent Ascent Methods for 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 epoch-wise stochastic gradient descent ascent for a general strongly-convex strongly-concave problem without smoothness or structural assumptions | Epoch-GDA · General SCSC min-max | iteration complexity for ε-duality gap: O\left(1/\epsilon\right) | Helped |
| Use epoch-wise updates with regularization of the primal variable for a general weakly-convex strongly-concave problem, without smoothness or structural assumptions | Epoch-GDA · General WCSC min-max | iteration complexity for nearly ε-stationary point: \tilde O\left(1/\epsilon^4\right) | Helped |
Closest papers by meaning
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.91)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.90)
- Fundamental Benefit of Alternating Updates in Minimax Optimization (ICML 2024 · similarity 0.89)
- Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems (ICML 2025 · similarity 0.89)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.88)
- Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints (NeurIPS 2024 · similarity 0.88)
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.