Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Annals of Statistics Year : 2021

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

Bernard Bercu
  • Function : Author
  • PersonId : 845707
Jérémie Bigot
  • Function : Author
  • PersonId : 983710

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.

Dates and versions

hal-02864967 , version 1 (11-06-2020)

Identifiers

Cite

Bernard Bercu, Jérémie Bigot. Asymptotic distribution and convergence rates of stochastic algorithms for entropic optimal transportation between probability measures. Annals of Statistics, 2021, 49 (2), pp.968-987. ⟨10.1214/20-AOS1987⟩. ⟨hal-02864967⟩

Collections

CNRS
41 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More