8 citations · 11 across the 3 of their papers we have counts for
3 papers
Dissecting adaptive methods in GANs
Samy Jelassi, David Dobre, Arthur Mensch +2
Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to pinpoint the "marginal value of adaptive…
A mean-field analysis of two-player zero-sum games
Carles Domingo-Enrich, Samy Jelassi, Arthur Mensch +2
Finding Nash equilibria in two-player zero-sum continuous games is a central problem in machine learning, e.g. for training both GANs and robust models. The existence of pure Nash…
Extragradient with player sampling for faster Nash equilibrium finding
Carles Domingo Enrich, Samy Jelassi, Carles Domingo-Enrich +3
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…