Skip to Main content Skip to Navigation
Journal articles

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

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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00915365
Contributor : Arnaud Guillin <>
Submitted on : Saturday, December 7, 2013 - 4:08:17 PM
Last modification on : Saturday, March 28, 2020 - 2:12:46 AM
Document(s) archivé(s) le : Saturday, March 8, 2014 - 12:20:19 AM

Files

fournier-guillin-wass.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00915365, version 1
  • ARXIV : 1312.2128

Citation

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

Share

Metrics

Record views

832

Files downloads

2545