Behavior of the Wasserstein distance between the empirical and the marginal distributions of stationary -dependent sequences

DOI10.3150/16-BEJ805zbMATH Open1392.60007arXiv1503.00113OpenAlexW2962759274MaRDI QIDQ527481FDOQ527481

Jérôme Dedecker, Florence Merlevède

Publication date: 11 May 2017

Published in: Bernoulli (Search for Journal in Brave)

Abstract: We study the Wasserstein distance of order 1 between the empirical distribution and the marginal distribution of stationary $alpha$-dependent sequences. We prove some moments inequalities of order p for any p $ge$ 1, and we give some conditions under which the central limit theorem holds. We apply our results to unbounded functions of expanding maps of the interval with a neutral fixed point at zero. The moment inequalities for the Wasserstein distance are similar to the well known von Bahr-Esseen or Rosenthal bounds for partial sums, and seem to be new even in the case of independent and identically distributed random variables.

Full work available at URL: https://arxiv.org/abs/1503.00113

Recommendations

• Wasserstein and total variation distance between marginals of Lévy processes
• Evolution of the Wasserstein distance between the marginals of two Markov processes
• Behavior of the empirical Wasserstein distance in \({\mathbb R}^d\) under moment conditions
• Central limit theorems for the Wasserstein distance between the empirical and the true distributions
• Precise limit in Wasserstein distance for conditional empirical measures of Dirichlet diffusion processes
• On the Wasserstein distance for a martingale central limit theorem
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Almost sure invariance principle for the Kantorovich distance between the empirical and the marginal distributions of strong mixing sequences
• Limit theorems in Wasserstein distance for empirical measures of diffusion processes on Riemannian manifolds

zbMATH Keywords

central limit theoremempirical processWasserstein distanceintermittencystationary sequencesmoments inequalities

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Central limit and other weak theorems (60F05) Functional limit theorems; invariance principles (60F17)

Cited In (8)

• Empirical measures and random walks on compact spaces in the quadratic Wasserstein metric
• Distribution of Distances based Object Matching: Asymptotic Inference
• Behavior of the empirical Wasserstein distance in \({\mathbb R}^d\) under moment conditions
• Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
• Simultaneous inference for autocovariances based on autoregressive sieve bootstrap
• Almost sure invariance principle for the Kantorovich distance between the empirical and the marginal distributions of strong mixing sequences
• The Berry–Esseen-type bound for the G-M estimator in a nonparametric regression model with α-mixing errors
• Bures distance and transition probability for \(\alpha\)-CPD-kernels

This page was built for publication: Behavior of the Wasserstein distance between the empirical and the marginal distributions of stationary \(\alpha\)-dependent sequences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q527481)