Research map / Optimization / Nonconvex and smooth optimization
Approaching the Global Nash Equilibrium of Non-Convex Multi-Player Games
Guanpu Chen, Gehui Xu, Fengxiang He, Yiguang Hong, Leszek Rutkowski, Dacheng Tao
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 Algorithm 1 instead of PGD, penalty, SGD or proximal methods | gradient-based baselines · Sensor localization, init x11^0=-3, 200 iterations | MLE: 0.0379 vs 3.8488 (proximal), 7.2688 (PGD) | Improved |
| use Algorithm 1 instead of baselines from init x11^0=-0.1 | baselines · Sensor localization, init x11^0=-0.1, 200 iterations | MLE: 0.0028 vs 4.4875 (penalty) | Improved |
| use Algorithm 1 when initial point is near the global NE (x11^0=3) | baselines · Sensor localization, init x11^0=3, 50 iterations | MLE: 0.3009 vs 0.1174 (PGD) | No clear effect |
| use Algorithm 1 at 200 iterations when init x11^0=3 | baselines · Sensor localization, init x11^0=3, 200 iterations | MLE: 0.0021 vs 0.0343 (proximal) | Improved |
| use Algorithm 1 instead of GD, OMD, EG with initial points [-4,-4] and [0,-3] | GD, OMD, EG · Robust neural network training (two-player adversarial) | convergence to global NE: only Algorithm 1 reaches global NE; others stuck at Nash stationary point | Improved |
| use Algorithm 1 with initial points [2,-2.5] and [3.5,4.25] | GD, OMD, EG · Robust neural network training (two-player adversarial) | convergence to global NE: all methods find the global NE | No clear effect |
Closest papers by meaning
- Competitive Gradient Descent (NeurIPS 2019 · similarity 0.90)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.89)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.89)
- Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics (NeurIPS 2025 · similarity 0.88)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.88)
- Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games (ICML 2025 · 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.
