Convergence of the empirical measure in expected wasserstein distance: non-asymptotic explicit bounds in ℝd

DOI10.1051/PS/2023011MaRDI QIDQ6133929zbMATH OpenOpenAlexFDO

Authors

Publication date 21 August 2023

Published in ESAIM: Probability and Statistics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2209.00923

zbMATH Keywords

empirical measureoptimal transportationsequence of i.i.d. random variables

Mathematics Subject Classification ID

(L^p)-limit theorems (60F25) Monte Carlo methods (65C05)

Abstract: We provide some non asymptotic bounds, with explicit constants, that measure the rate of convergence, in expected Wasserstein distance, of the empirical measure associated to an i.i.d. $N$-sample of a given probability distribution on $mathbb{R}^d$.

Recommendations

• On the rate of convergence in Wasserstein distance of the empirical measure
• Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
• Mean rates of convergence of empirical measures in the Wasserstein metric
• On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance

Cited in

(20)

• Precise limit in Wasserstein distance for conditional empirical measures of Dirichlet diffusion processes
• Approximation rate in Wasserstein distance of probability measures on the real line by deterministic empirical measures
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Generalized Wasserstein distance and weak convergence of sublinear expectations
• On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• Non-monotone convergence in the quadratic Wasserstein distance
• Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
• Convergence and finite sample approximations of entropic regularized Wasserstein distances in Gaussian and RKHS settings
• Optimal Matching of Random Samples and Rates of Convergence of Empirical Measures
• Bounds in \(L^1\) Wasserstein distance on the normal approximation of general M-estimators
• Convergence of adapted empirical measures on \(\mathbb{R}^d\)
• Optimal matching problem on the Boolean cube
• Learning conditional distributions on continuous spaces
• Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities
• Distributionally robust optimization
• Convergence of empirical optimal transport in unbounded settings
• The distributionally robust prediction error of the \(\sqrt{\mathrm{LASSO}}\) and related estimators
• Uniform-in-time estimates on corrections to mean field for interacting Brownian particles
• On a class of modified Wasserstein distances induced by concave mobility functions defined on bounded intervals

This page was built for publication: Convergence of the empirical measure in expected wasserstein distance: non-asymptotic explicit bounds in ℝ^d

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6133929)