Research map / Optimization / Nonconvex and smooth optimization
Provably convergent quasistatic dynamics for mean-field two-player zero-sum games
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 QSLGD instead of LGDA | Langevin particle optimization · 1-dimensional game on torus, large β (weak entropy regularization) | KL divergence | Helped |
| Use QSLGD instead of LGDA | Langevin particle optimization · 1-dimensional game on torus, small β | KL divergence | No clear effect |
| Increase the number of QSLGD inner iterations | QSLGD · 1-dimensional game on torus, large β | KL divergence | Helped |
| Use QSLGD instead of LGDA | Langevin particle optimization · 1-dimensional game on torus, small step length | KL divergence | Helped |
| Use QSLGD instead of LGDA | Langevin particle optimization · 1-dimensional game on torus, large step length | KL divergence | Hurt |
| Increase the step length | QSLGD inner loop · 1-dimensional game on torus | KL divergence | Hurt |
| Use QSLGD instead of LGDA | Langevin particle optimization · Polynomial games on spheres | NI error | No clear effect |
| Train a mixture of generators and discriminators with QSLGD | Mixture of GANs · Gaussian mixtures with 4 and 8 modes | qualitative generation success | Helped |
| Train QSLGD on high-dimensional Gaussian mixtures | Mixture of GANs · High-dimensional Gaussian mixtures | average squared distance to closest mode center: reduced to 0.3-0.5 after 10000 iterations | Helped |
Closest papers by meaning
- A mean-field analysis of two-player zero-sum games (NeurIPS 2020 · similarity 0.93)
- Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field Perspective (ICML 2023 · similarity 0.90)
- Competitive Gradient Descent (NeurIPS 2019 · similarity 0.90)
- Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems (ICLR 2024 · similarity 0.89)
- Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization (ICLR 2024 · similarity 0.86)
- Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis (NeurIPS 2024 · similarity 0.86)
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.