Research map / Optimization / Nonconvex and smooth optimization
SAPD+: An Accelerated Stochastic Method for Nonconvex-Concave Minimax Problems
Xuan Zhang, Necdet Aybat, Mert Gurbuzbalaban
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 changed | Where | Measured | Effect |
|---|---|---|---|
| SAPD+ vs best other algorithm | DRO · a9a | average training accuracy: 75.92% -> 84.06% | Improved |
| SAPD+VR vs best other algorithm | DRO · a9a | average training accuracy: 75.92% -> 84.33% | Improved |
| SAPD+ vs best other algorithm | DRO · gisette | average training accuracy: 93.07% -> 95.41% | Improved |
| SAPD+VR vs best other algorithm | DRO · gisette | average training accuracy: 93.07% -> 97.69% | Improved |
| SAPD+ vs best other algorithm | DRO · sido0 | average training accuracy: 96.43% -> 96.43% | No clear effect |
| SAPD+VR vs best other algorithm | DRO · sido0 | average training accuracy: 96.43% -> 97.46% | Improved |
| SAPD+VR vs SREDA and SMDA-VR | fair classification CNN · MNIST, F-MNIST, CIFAR10 | average loss and loss std | Improved |
Closest papers by meaning
- Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems (ICML 2020 · similarity 0.91)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.90)
- Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems (NeurIPS 2020 · similarity 0.90)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.90)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.89)
- Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax 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.
