Research map / Optimization / Nonconvex and smooth optimization
Finding Second-Order Stationary Points in Nonconvex-Strongly-Concave Minimax Optimization
Luo Luo, Yujun Li, Cheng Chen
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 MCN (cubic Newton on x, AGD on y) instead of GDA | MCN · Synthetic minimax, far initial point (x2,y2) | convergence speed (running time vs P(x)-P*) | Improved |
| use MCN instead of GDA when starting near the strict saddle point | MCN · Synthetic minimax, near initial point (x1,y1) | minimum Hessian eigenvalue of P(x) | Improved |
| use IMCN instead of GDA on DANN domain adaptation | IMCN · MNIST to MNIST-m | running time and oracle calls | Improved |
| use IMCN instead of GDA on DANN domain adaptation | IMCN · MNIST-m to MNIST | running time and oracle calls | Improved |
Closest papers by meaning
- Efficient Algorithms for Smooth Minimax Optimization (NeurIPS 2019 · similarity 0.91)
- Second-Order Min-Max Optimization with Lazy Hessians (ICLR 2025 · similarity 0.91)
- The Computational Complexity of Finding Second-Order Stationary Points (ICML 2024 · similarity 0.89)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · similarity 0.88)
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity (NeurIPS 2025 · similarity 0.88)
- On The Complexity of First-Order Methods in Stochastic Bilevel Optimization (ICML 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.
