Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices

Guillaume Wang · Lénaïc Chizat

Great Hall & Hall B1+B2 (level 1) #1125
[ ]
Wed 13 Dec 3 p.m. PST — 5 p.m. PST

Abstract: We study the convergence to local Nash equilibria of gradient methods for two-player zero-sum differentiable games.It is well-known that, in the continuous-time setting, such dynamics converge locally when $S \succ 0$ and may diverge when $S=0$, where $S\succeq 0$ is the symmetric part of the Jacobian at equilibrium that accounts for the "potential" component of the game. We show that these dynamics also converge as soon as $S$ is nonzero (*partial curvature*) and the eigenvectors of the antisymmetric part $A$ are in general position with respect to the kernel of $S$.We then study the convergence rate when $S \ll A$ and prove that it typically depends on the *average* of the eigenvalues of $S$, instead of the minimum as an analogy with minimization problems would suggest.To illustrate our results, we consider the problem of computing mixed Nash equilibria of continuous games. We show that, thanks to partial curvature, conic particle methods -- which optimize over both weights and supports of the mixed strategies -- generically converge faster than fixed-support methods.For min-max games, it is thus beneficial to add degrees of freedom "with curvature": this can be interpreted as yet another benefit of over-parameterization.

Chat is not available.