Empirical measures and random walks on compact spaces in the quadratic Wasserstein metric

DOI10.1214/22-AIHP1322zbMATH Open1530.60041arXiv2110.00295OpenAlexW3203438058MaRDI QIDQ6147698FDOQ6147698

Authors: Bence Borda 

Publication date: 16 January 2024

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Abstract: Estimating the rate of convergence of the empirical measure of an i.i.d. sample to the reference measure is a classical problem in probability theory. Extending recent results of Ambrosio, Stra and Trevisan on 2-dimensional manifolds, in this paper we prove sharp asymptotic and nonasymptotic upper bounds for the mean rate in the quadratic Wasserstein metric $W_2$ on a $d$-dimensional compact Riemannian manifold. Under a smoothness assumption on the reference measure, our bounds match the classical rate in the optimal matching problem on the unit cube due to Ajtai, Koml'os, Tusn'ady and Talagrand. The i.i.d. condition is relaxed to stationary samples with a mixing condition. As an example of a nonstationary sample, we also consider the empirical measure of a random walk on a compact Lie group. Surprisingly, on semisimple groups random walks attain almost optimal rates even without a spectral gap assumption. The proofs are based on Fourier analysis, and in particular on a Berry-Esseen smoothing inequality for $W_2$ on compact manifolds, a result of independent interest with a wide range of applications.

Full work available at URL: https://arxiv.org/abs/2110.00295

zbMATH Keywords

optimal transportationRiemannian manifoldBerry-Esseen inequalityheat kerneloccupation measureLie group

Mathematics Subject Classification ID

Optimal transportation (49Q22) Stationary stochastic processes (60G10) Sums of independent random variables; random walks (60G50) Probability measures on groups or semigroups, Fourier transforms, factorization (60B15)

Cites Work

• Basic properties of strong mixing conditions. A survey and some open questions
• On optimal matchings
• Riemannian manifolds with uniformly bounded eigenfunctions
• Foundations of quantization for probability distributions
• Title not available (Why is that?)
• Title not available (Why is that?)
• On polynomial mixing bounds for stochastic differential equations
• Approximation by finitely supported measures
• Some Limit Theorems for Random Functions. I
• Title not available (Why is that?)
• On the rate of convergence in Wasserstein distance of the empirical measure
• Ergodicity and exponential \(\beta\)-mixing bounds for multidimensional diffusions with jumps
• On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
• Symmetric Random Walks on Groups
• On the spectral gap for finitely-generated subgroups of \(\text{SU}(2)\)
• A spectral gap theorem in simple Lie groups
• Random walks in compact groups
• A spectral gap theorem in SU\((d)\)
• Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
• Matching random samples in many dimensions
• Hecke operators and distributing points on the sphere I
• Hecke operators and distributing points on S². II
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Probabilities on a Compact Group
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Title not available (Why is that?)
• Behavior of the Wasserstein distance between the empirical and the marginal distributions of stationary \(\alpha\)-dependent sequences
• Subgeometric ergodicity and β-mixing
• Transport inequalities on Euclidean spaces for non-Euclidean metrics
• Automorphic forms and the distribution of points on odd-dimensional spheres.
• The Ruziewicz problem and distributing points on homogeneous spaces of a compact Lie group
• Wasserstein distance, Fourier series and applications
• On the Wasserstein distance between classical sequences and the Lebesgue measure
• Comparison between W₂ distance and Ḣ⁻¹ norm, and Localization of Wasserstein distance
• A PDE approach to a 2-dimensional matching problem
• A Wasserstein inequality and minimal Green energy on compact manifolds
• Equidistribution of random walks on compact groups. II: The Wasserstein metric
• A simple Fourier analytic proof of the AKT optimal matching theorem
• Berry-Esseen smoothing inequality for the Wasserstein metric on compact Lie groups

Cited In (2)

• Annealed quantitative estimates for the quadratic 2D-discrete random matching problem
• Riesz energy, \(L^2\) discrepancy, and optimal transport of determinantal point processes on the sphere and the flat torus

This page was built for publication: Empirical measures and random walks on compact spaces in the quadratic Wasserstein metric

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6147698)