Extragradient with player sampling for faster Nash equilibrium finding - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Extragradient with player sampling for faster Nash equilibrium finding

Résumé

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.
Fichier principal
Vignette du fichier
article.pdf (1.48 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02142598 , version 1 (28-05-2019)
hal-02142598 , version 2 (29-05-2019)
hal-02142598 , version 3 (05-06-2019)
hal-02142598 , version 4 (02-03-2020)
hal-02142598 , version 5 (11-07-2020)

Identifiants

Citer

Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna. Extragradient with player sampling for faster Nash equilibrium finding. Proceedings of the International Conference on Machine Learning, 2020, Vienna, Austria. ⟨hal-02142598v5⟩
415 Consultations
276 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More