Skip to Main content Skip to Navigation
Conference papers

Extragradient with player sampling for faster Nash equilibrium finding

Abstract : 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-02142598
Contributor : Arthur Mensch <>
Submitted on : Saturday, July 11, 2020 - 12:18:03 PM
Last modification on : Tuesday, September 22, 2020 - 3:48:24 AM

Files

article.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02142598, version 5
  • ARXIV : 1905.12363

Collections

Citation

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⟩

Share

Metrics

Record views

85

Files downloads

99