6 papers · 1 filter
Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization
Guillaume Wang
The Sinkhorn algorithm is the de facto standard method for numerically solving entropy-regularized optimal transport problems over finite sets. In this work, we investigate a pheno…
Sharp convergence rate for the Sinkhorn algorithm via a local analysis
Guillaume Wang
We prove that the Sinkhorn algorithm converges at the rate of in -norm marginal error and in joint relative entropy, which is known to be sharp in the asymptotical…
Almost-sharp convergence rate for the Sinkhorn algorithm in the asymptotically scalable case
Guillaume Wang
We prove that the Sinkhorn algorithm converges at a rate of in -norm marginal error, in the asymptotically scalable case. This almost closes the gap betw…
Local convergence of mean-field Langevin dynamics: from gradient flows to linearly monotone games
Guillaume Wang, Lénaïc Chizat
We study the local convergence of diffusive mean-field systems, including Wasserstein gradient flows, min-max dynamics, and multi-species games. We establish exponential local conv…
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
Guillaume Wang, Alireza Mousavi-Hosseini, Lénaïc Chizat
Mean-field Langevin dynamics (MLFD) is a class of interacting particle methods that tackle convex optimization over probability measures on a manifold, which are scalable, versatil…
Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices
Guillaume Wang, Lénaïc Chizat
We study the convergence to local Nash equilibria of gradient methods for two-player zero-sum differentiable games. It is well-known that such dynamics converge locally when $S \su…