Small-Gain Nash: Certified Contraction to Nash Equilibria in Differentiable Games

TL;DR

This paper introduces Small-Gain Nash (SGN), a new geometric framework that certifies convergence of gradient-based learning in complex differentiable games by transforming local game properties into a contraction guarantee.

Contribution

SGN provides a novel block-weighted geometry that certifies contraction and convergence in non-monotone games, extending classical monotonicity-based guarantees.

Findings

SGN successfully certifies convergence in quadratic games where Euclidean analysis fails.

The framework extends to mirror and Fisher geometries for policy gradient methods.

An offline pipeline estimates parameters and computes safe step-sizes for non-monotone games.

Abstract

Classical convergence guarantees for gradient-based learning in games require the pseudo-gradient to be (strongly) monotone in Euclidean geometry as shown by rosen(1965), a condition that often fails even in simple games with strong cross-player couplings. We introduce Small-Gain Nash (SGN), a block small-gain condition in a custom block-weighted geometry. SGN converts local curvature and cross-player Lipschitz coupling bounds into a tractable certificate of contraction. It constructs a weighted block metric in which the pseudo-gradient becomes strongly monotone on any region where these bounds hold, even when it is non-monotone in the Euclidean sense. The continuous flow is exponentially contracting in this designed geometry, and projected Euler and RK4 discretizations converge under explicit step-size bounds derived from the SGN margin and a local Lipschitz constant. Our analysis reveals a certified "timescale band", a non-asymptotic, metric-based certificate that plays a TTUR-like role: rather than forcing asymptotic timescale separation via vanishing, unequal step sizes, SGN identifies a finite band of relative metric weights for which a single-step-size dynamics is provably contractive. We validate the framework on quadratic games where Euclidean monotonicity analysis fails to predict convergence, but SGN successfully certifies it, and extend the construction to mirror/Fisher geometries for entropy-regularized policy gradient in Markov games. The result is an offline certification pipeline that estimates curvature, coupling, and Lipschitz parameters on compact regions, optimizes block weights to enlarge the SGN margin, and returns a structural, computable convergence certificate consisting of a metric, contraction rate, and safe step-sizes for non-monotone games.