Coupled Wasserstein Gradient Flows for Min-Max and Cooperative Games

TL;DR

This paper introduces a Wasserstein gradient flow framework for analyzing two-player infinite-dimensional games, providing convergence results and applications to economics, loan processing, and predictive modeling.

Contribution

It develops a novel coupled PDE framework for min-max and cooperative games in Wasserstein space, with convergence analysis and practical applications.

Findings

Exponential convergence to Nash equilibrium under convexity.

Application to real-world data demonstrating distribution-level modeling.

Convergence results in timescale-separated strategic interactions.

Abstract

We propose a framework for two-player infinite-dimensional games with cooperative or competitive structure. These games take the form of coupled partial differential equations in which players optimize over a space of measures, driven by either a gradient descent or gradient descent-ascent in Wasserstein-2 space. We characterize the properties of the Nash equilibrium of the system, and relate it to the steady state of the dynamics. In the min-max setting, we show, under sufficient convexity conditions, that solutions converge exponentially fast and with explicit rate to the unique Nash equilibrium. Similar results are obtained for the cooperative setting. We apply this framework to distribution shift induced by interactions among a strategic population of agents and an algorithm, proving additional convergence results in the timescale-separated setting. We illustrate the performance of our model on (i) real data from an economics study on Colombia census data, (ii) feature modification in loan applications, and (iii) performative prediction. The numerical experiments demonstrate the importance of distribution-level, rather than moment-level, modeling.