Research map / Optimization / Nonconvex and smooth optimization
Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave 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 |
|---|---|---|---|
| Use recursive variance-reduced gradient estimates with the multi-step concave maximizer | SGDA for stochastic nonconvex-strongly-concave minimax · Stochastic minimax | stochastic gradient evaluations: \fO(\kappa^3{\varepsilon}^{-4}) -> \fO(\kappa^3{\varepsilon}^{-3}) | Helped |
| Use finite-sum SREDA instead of Minimax PPA when n≥κ² | Finite-sum nonconvex-strongly-concave minimax · Finite-sum minimax, n≥κ² | stochastic gradient evaluations: \tilde\fO(\kappa^{1/2}n{\varepsilon}^{-2}) -> \tilde\fO\left(n + \kappa^2n^{1/2}{\varepsilon}^{-2}\right) | Helped |
| Apply SREDA to the six robust-optimization datasets | SREDA and baseline algorithms · a9a, w8a, gisette, mushrooms, sido0, rcv1 | convergence speed | Helped |
Closest papers by meaning
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.91)
- Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization (NeurIPS 2020 · similarity 0.91)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.90)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · similarity 0.88)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.88)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (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.