AI Chat AI Image Generator AI Video Text to Speech

A Central Limit Theorem for Wasserstein type distances between two different laws

10/26/2017

∙

by Philippe Berthet, et al.

∙

∙

This article is dedicated to the estimation of Wasserstein distances and Wasserstein costs between two distinct continuous distributions F and G on R. The estimator is based on the order statistics of (possibly dependent) samples of F resp. G. We prove the consistency and the asymptotic normality of our estimators. Keywords: Central Limit Theorems- Generelized Wasserstein distances- Empirical processes- Strong approximation- Dependent samples.

Philippe Berthet
7 publications
Jean-Claude Fort
4 publications
Thierry Klein
13 publications

page 1

page 2

page 3

page 4

research

∙ 06/01/2022

Distributional Convergence of the Sliced Wasserstein Process

Motivated by the statistical and computational challenges of computing W...

0 Jiaqi Xi, et al. ∙

research

∙ 11/06/2019

Weak convergence of empirical Wasserstein type distances

We estimate contrasts ∫_0 ^1 ρ(F^-1(u)-G^-1(u))du between two continuous...

0 Philippe Berthet, et al. ∙

research

∙ 07/23/2021

Signature asymptotics, empirical processes, and optimal transport

Rough path theory provides one with the notion of signature, a graded fa...

0 Thomas Cass, et al. ∙

research

∙ 05/07/2023

Wasserstein distance bounds on the normal approximation of empirical autocovariances and cross-covariances under non-stationarity and stationarity

The autocovariance and cross-covariance functions naturally appear in ma...

0 Andreas Anastasiou, et al. ∙

research

∙ 03/09/2019

Orthogonal Estimation of Wasserstein Distances

Wasserstein distances are increasingly used in a wide variety of applica...

7 Mark Rowland, et al. ∙

research

∙ 04/27/2020

Limit laws for the norms of extremal samples

Let denote S_n(p) = k_n^-1∑_i=1^k_n( log (X_n+1-i,n / X_n-k_n, n) )^p, w...

0 Péter Kevei, et al. ∙

research

∙ 07/09/2023

Wasserstein-p Bounds in the Central Limit Theorem Under Local Dependence

The central limit theorem (CLT) is one of the most fundamental results i...

0 Tianle Liu, et al. ∙