Extra-gradient with player sampling for faster convergence in n-player games

Samy Jelassi · Carles Domingo-Enrich · Damien Scieur · Arthur Mensch · Joan Bruna

Keywords: [ Convex Optimization ] [ Game Theory and Mechanism Design ] [ Generative Adversarial Networks ] [ Learning Theory ]

[ Abstract ] [ Join Zoom
Please do not share or post zoom links


Data-driven modeling increasingly requires to find a Nash equilibrium in multi-player games, e.g. when training GANs. In this paper, we analyse a new extra-gradient method for Nash equilibrium finding, that performs gradient extrapolations and updates on a random subset of players at each iteration. This approach provably exhibits a better rate of convergence than full extra-gradient for non-smooth convex games with noisy gradient oracle. We propose an additional variance reduction mechanism to obtain speed-ups in smooth convex games. Our approach makes extrapolation amenable to massive multiplayer settings, and brings empirical speed-ups, in particular when using a heuristic cyclic sampling scheme. Most importantly, it allows to train faster and better GANs and mixtures of GANs.

Chat is not available.