3 papers
math.OC2025
Doubly Regularized Entropic Wasserstein Barycenters
Lénaïc Chizat
We study a general formulation of regularized Wasserstein barycenters that enjoys favorable regularity, approximation, stability and (grid-free) optimization properties. This baryc…
math.OC2025
Sharper Exponential Convergence Rates for Sinkhorn's Algorithm in Continuous Settings
Lénaïc Chizat, Alex Delalande, Tomas VaÅ¡keviÄius
We study the convergence rate of Sinkhorn's algorithm for solving entropy-regularized optimal transport problems when at least one of the probability measures, , admits a densi…
stat.ML2024
Deep linear networks for regression are implicitly regularized towards flat minima
Pierre Marion, Lénaïc Chizat
The largest eigenvalue of the Hessian, or sharpness, of neural networks is a key quantity to understand their optimization dynamics. In this paper, we study the sharpness of deep l…