On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games

TL;DR

This paper introduces a new two-timescale algorithm called local symplectic surgery that guarantees convergence exclusively to local Nash equilibria in two-player zero-sum games, overcoming limitations of previous gradient methods.

Contribution

The paper develops a novel algorithm leveraging the differential structure of zero-sum games to ensure convergence only to local Nash equilibria, avoiding non-Nash stationary points.

Findings

Algorithm converges to local Nash equilibria without oscillations.

Per-iteration complexity matches existing algorithms.

Validated on toy examples and GAN training.

Abstract

We propose local symplectic surgery, a two-timescale procedure for finding local Nash equilibria in two-player zero-sum games. We first show that previous gradient-based algorithms cannot guarantee convergence to local Nash equilibria due to the existence of non-Nash stationary points. By taking advantage of the differential structure of the game, we construct an algorithm for which the local Nash equilibria are the only attracting fixed points. We also show that the algorithm exhibits no oscillatory behaviors in neighborhoods of equilibria and show that it has the same per-iteration complexity as other recently proposed algorithms. We conclude by validating the algorithm on two numerical examples: a toy example with multiple Nash equilibria and a non-Nash equilibrium, and the training of a small generative adversarial network (GAN).