Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games

Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Georgios Piliouras

Oct-2-2025, 22:47:10 GMT–Neural Information Processing Systems

We study a wide class of non-convex non-concave min-max games that generalizes over standard bilinear zero-sum games.

artificial intelligence, machine learning, optimization problem, (19 more...)

Neural Information Processing Systems

Oct-2-2025, 22:47:10 GMT

Conferences PDF

Country:
- Europe (1.00)
- Asia (0.93)
- North America > United States
  - California > Los Angeles County (0.28)

Technology:
- Information Technology
  - Game Theory (1.00)
  - Artificial Intelligence
    - Representation & Reasoning
      - Optimization (0.46)
      - Agents (0.46)
    - Machine Learning
      - Neural Networks (0.48)
      - Statistical Learning > Gradient Descent (0.43)

Duplicate Docs Excel Report

Title
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games

Similar Docs Excel Report more

Title	Similarity	Source
None found