Skip to Main content Skip to Navigation
Journal articles

Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures

Abstract : This paper is devoted to the stochastic approximation of entropically regularized Wasserstein distances between two probability measures, also known as Sinkhorn divergences. The semi-dual formulation of such regularized optimal transportation problems can be rewritten as a non-strongly concave optimisation problem. It allows to implement a Robbins-Monro stochastic algorithm to estimate the Sinkhorn divergence using a sequence of data sampled from one of the two distributions. Our main contribution is to establish the almost sure convergence and the asymptotic normality of a new recursive estimator of the Sinkhorn divergence between two probability measures in the discrete and semi-discrete settings. We also study the rate of convergence of the expected excess risk of this estimator in the absence of strong concavity of the objective function. Numerical experiments on synthetic and real datasets are also provided to illustrate the usefulness of our approach for data analysis.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/hal-02864967
Contributor : Jérémie Bigot <>
Submitted on : Thursday, June 11, 2020 - 2:26:10 PM
Last modification on : Friday, June 12, 2020 - 3:46:17 AM

Links full text

Identifiers

  • HAL Id : hal-02864967, version 1
  • ARXIV : 1812.09150

Collections

CNRS | IMB

Citation

Bernard Bercu, Jérémie Bigot. Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures. Annals of Statistics, Institute of Mathematical Statistics, In press. ⟨hal-02864967⟩

Share

Metrics

Record views

21