On the rate of convergence in Wasserstein distance of the empirical measure - Archive ouverte HAL Access content directly
Journal Articles Probability Theory and Related Fields Year : 2015

On the rate of convergence in Wasserstein distance of the empirical measure

(1) , (2)
1
2

Abstract

Let $\mu_N$ be the empirical measure associated to a $N$-sample of a given probability distribution $\mu$ on $\mathbb{R}^d$. We are interested in the rate of convergence of $\mu_N$ to $\mu$, when measured in the Wasserstein distance of order $p>0$. We provide some satisfying non-asymptotic $L^p$-bounds and concentration inequalities, for any values of $p>0$ and $d\geq 1$. We extend also the non asymptotic $L^p$-bounds to stationary $\rho$-mixing sequences, Markov chains, and to some interacting particle systems.
Fichier principal
Vignette du fichier
fournier-guillin-wass.pdf (282.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00915365 , version 1 (07-12-2013)

Identifiers

Cite

Nicolas Fournier, Arnaud Guillin. On the rate of convergence in Wasserstein distance of the empirical measure. Probability Theory and Related Fields, 2015, 162 (3-4), pp.707. ⟨hal-00915365⟩
548 View
2928 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More