Simultaneous Transport Evolution for Minimax Equilibria on Measures

02/14/2022
by   Carles Domingo Enrich, et al.
0

Min-max optimization problems arise in several key machine learning setups, including adversarial learning and generative modeling. In their general form, in absence of convexity/concavity assumptions, finding pure equilibria of the underlying two-player zero-sum game is computationally hard [Daskalakis et al., 2021]. In this work we focus instead in finding mixed equilibria, and consider the associated lifted problem in the space of probability measures. By adding entropic regularization, our main result establishes global convergence towards the global equilibrium by using simultaneous gradient ascent-descent with respect to the Wasserstein metric – a dynamics that admits efficient particle discretization in high-dimensions, as opposed to entropic mirror descent. We complement this positive result with a related entropy-regularized loss which is not bilinear but still convex-concave in the Wasserstein geometry, and for which simultaneous dynamics do not converge yet timescale separation does. Taken together, these results showcase the benign geometry of bilinear games in the space of measures, enabling particle dynamics with global qualitative convergence guarantees.

READ FULL TEXT
02/14/2020

A mean-field analysis of two-player zero-sum games

Finding Nash equilibria in two-player zero-sum continuous games is a cen...
06/30/2022

A note on large deviations for interacting particle dynamics for finding mixed equilibria in zero-sum games

Finding equilibria points in continuous minimax games has become a key p...
10/28/2019

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

We study a wide class of non-convex non-concave min-max games that gener...
01/13/2021

Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent

Many recent AI architectures are inspired by zero-sum games, however, th...
09/30/2020

Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation

We study the role that a finite timescale separation parameter τ has on ...
10/07/2020

A Robust Framework for Analyzing Gradient-Based Dynamics in Bilinear Games

In this work, we establish a frequency-domain framework for analyzing gr...
06/17/2020

Competitive Mirror Descent

Constrained competitive optimization involves multiple agents trying to ...