Research map / Optimization / Nonconvex and smooth optimization
Proximal Gradient Descent-Ascent: Variable Convergence under KŁ Geometry
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 proximal-GDA under KŁ geometry with θ=1 | Proximal-GDA · Regularized nonconvex-strongly-concave minimax | Variable convergence rate: Finite number of iterations | Helped |
| Use proximal-GDA under KŁ geometry with θ∈(1/2, 1) | Proximal-GDA · Regularized nonconvex-strongly-concave minimax | Variable convergence rate: \mathcal{O}\Big( \exp\Big(-\big(\frac{1}{2(1-\theta)}\big)^{t-t_0}\Big)\Big) | Helped |
| Use proximal-GDA under KŁ geometry with θ=1/2 | Proximal-GDA · Regularized nonconvex-strongly-concave minimax | Variable convergence rate: \mathcal{O}\Big(\Big(\min\Big\{2, 1+\frac{1}{2Mc^2}\Big\}\Big)^{(t_0-t)/2}\Big) | Helped |
| Use proximal-GDA under KŁ geometry with θ∈(0, 1/2) | Proximal-GDA · Regularized nonconvex-strongly-concave minimax | Variable convergence rate: \mathcal{O}\Big((t-t_0)^{-\frac{\theta}{1-2\theta}}\Big) | Helped |
Closest papers by meaning
- Fundamental Benefit of Alternating Updates in Minimax Optimization (ICML 2024 · similarity 0.91)
- Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization (NeurIPS 2023 · similarity 0.90)
- On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems (ICML 2020 · similarity 0.90)
- Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems (NeurIPS 2020 · similarity 0.90)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.89)
- Adaptive Proximal Gradient Method for 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.