HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Extra-gradient with player sampling for provable fast convergence in n-player games

Abstract : Data-driven model training is increasingly relying on finding Nash equilibria with provable techniques, e.g., for GANs and multi-agent RL. In this paper, we analyse a new extra-gradient method, that performs gradient extrapolations and updates on a random subset of players at each iteration. This approach provably exhibits the same rate of convergence as full extra-gradient in non-smooth convex games. We propose an additional variance reduction mechanism for this to hold for smooth convex games. Our approach makes extrapolation amenable to massive multiplayer settings, and brings empirical speed-ups, in particular when using cyclic sampling schemes. We demonstrate the efficiency of player sampling on large-scale non-smooth and non-strictly convex games. We show that the joint use of extrapolation and player sampling allows to train better GANs on CIFAR10.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Contributor : Arthur Mensch Connect in order to contact the contributor
Submitted on : Monday, March 2, 2020 - 5:11:54 PM
Last modification on : Thursday, March 17, 2022 - 10:08:19 AM


Files produced by the author(s)


  • HAL Id : hal-02142598, version 4
  • ARXIV : 1905.12363


Samy Jelassi, Carles Domingo Enrich, Damien Scieur, Arthur Mensch, Joan Bruna. Extra-gradient with player sampling for provable fast convergence in n-player games. 2020. ⟨hal-02142598v4⟩



Record views


Files downloads