An improved central limit theorem and fast convergence rates for entropic transportation costs

04/19/2022
by   Eustasio del Barrio, et al.
0

We prove a central limit theorem for the entropic transportation cost between subgaussian probability measures, centered at the population cost. This is the first result which allows for asymptotically valid inference for entropic optimal transport between measures which are not necessarily discrete. In the compactly supported case, we complement these results with new, faster, convergence rates for the expected entropic transportation cost between empirical measures. Our proof is based on strengthening convergence results for dual solutions to the entropic optimal transport problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/12/2021

Central Limit Theorems for General Transportation Costs

We consider the problem of optimal transportation with general cost betw...
research
05/28/2019

Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem

We prove several fundamental statistical bounds for entropic OT with the...
research
02/13/2022

Central Limit Theorems for Semidiscrete Wasserstein Distances

We prove a Central Limit Theorem for the empirical optimal transport cos...
research
02/25/2020

A CLT in Stein's distance for generalized Wishart matrices and higher order tensors

We study the convergence along the central limit theorem for sums of ind...
research
12/04/2019

Asymptotics for Strassen's Optimal Transport Problem

In this paper, we consider Strassen's version of optimal transport probl...
research
06/20/2023

Convergence of Empirical Optimal Transport in Unbounded Settings

In compact settings, the convergence rate of the empirical optimal trans...
research
03/09/2022

An entropic generalization of Caffarelli's contraction theorem via covariance inequalities

The optimal transport map between the standard Gaussian measure and an α...

Please sign up or login with your details

Forgot password? Click here to reset