← Search

Flavien Léger

2 accepted papers

2022

Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EM

NeurIPS 2022accept

Many problems in machine learning can be formulated as optimizing a convex functional over a vector space of measures. This paper studies the convergence of the mirror descent algorithm in this infinite-dimensional setting. Defining Bregman divergences through directional derivatives, we derive the…

Cited by 36SourcePDFScholar
2020

Faster Wasserstein Distance Estimation with the Sinkhorn Divergence

NeurIPS 2020poster

The squared Wasserstein distance is a natural quantity to compare probability distributions in a non-parametric setting. This quantity is usually estimated with the plug-in estimator, defined via a discrete optimal transport problem which can be solved to $\epsilon$-accuracy by adding an entropic re…

Cited by 211SourcePDFScholar