Research map / Optimization / Nonconvex and smooth optimization
A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
Yuanyuan Liu, Fanhua Shang, Weixin An, Junhao Liu, Hongying Liu, Zhouchen Lin
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 |
|---|---|---|---|
| use EGDA instead of GDA, EG and FEG | synthetic NC-NC minimax · f(x,y)=x^2+3sin^2x sin^2y-4y^2-10sin^2y | convergence speed (distance to saddle point, gradient norm) | Improved |
| use EGDA instead of FEG despite FEG's O(1/t^2) theoretical rate under negative monotonicity | synthetic NC-NC minimax · f(x,y)=x^2+3sin^2x sin^2y-4y^2-10sin^2y | convergence speed | Improved |
| use EGDA instead of GDA and EAG | convex-concave problem · f(x,y)=log(1+e^x)+3xy-log(1+e^y) | distance to saddle point | Improved |
| GDA with same small step-size as other methods | GDA · convex-concave problem | convergence to stationary point | Hurt |
| use EGDA instead of GDA and MGDA for robust training | adversarial training (NC-C) · Fashion MNIST and MNIST | training loss convergence speed | Improved |
| use EGDA instead of Smoothed-GDA | adversarial training (NC-C) · Fashion MNIST and MNIST | training loss convergence speed | Improved |
Closest papers by meaning
- Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion (ICML 2024 · similarity 0.91)
- Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique (ICML 2024 · similarity 0.88)
- Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization (NeurIPS 2024 · similarity 0.88)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.88)
- Last-Iterate Convergence of Single-Loop Stochastic Methods for Constrained Convex-Concave Minimax Problems (NeurIPS 2026 · similarity 0.87)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · 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.
