On the mean speed of convergence of empirical and occupation measures in Wasserstein distance

DOI10.1214/12-AIHP517zbMATH Open1294.60005arXiv1105.5263OpenAlexW2952142002MaRDI QIDQ2451111FDOQ2451111

Authors: Emmanuel Boissard, Thibaut Le Gouic 

Publication date: 26 May 2014

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

Abstract: In this work, we provide non-asymptotic bounds for the average speed of convergence of the empirical measure in the law of large numbers, in Wasserstein distance. We also consider occupation measures of ergodic Markov chains. One motivation is the approximation of a probability measure by finitely supported measures (the quantization problem). It is found that rates for empirical or occupation measures match or are close to previously known optimal quantization rates in several cases. This is notably highlighted in the example of infinite-dimensional Gaussian measures.

Full work available at URL: https://arxiv.org/abs/1105.5263

Recommendations

• On the rate of convergence in Wasserstein distance of the empirical measure
• Mean rates of convergence of empirical measures in the Wasserstein metric
• Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
• Convergence of the empirical measure in expected wasserstein distance: non-asymptotic explicit bounds in ℝ^d
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• On the rate of convergence of empirical measure in \(\infty \)-Wasserstein distance for unbounded density function
• Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
• Convergence in Wasserstein distance for empirical measures of semilinear SPDEs
• Convergence in Wasserstein distance for empirical measures of Dirichlet diffusion processes on manifolds
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance

zbMATH Keywords

Markov chainsoptimal transportationWasserstein metricstransportation inequalitiesfunctional quantization

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Discrete-time Markov processes on general state spaces (60J05)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Title not available (Why is that?)
• On optimal matchings
• Asymptotics for transportation cost in high dimensions
• The concentration of measure phenomenon
• Combinatorial Optimization Over Two Random Point Sets
• Foundations of quantization for probability distributions
• The Speed of Mean Glivenko-Cantelli Convergence
• Bounding \(\bar d\)-distance by informational divergence: A method to prove measure concentration
• Hypercontractivity of Hamilton-Jacobi equations.
• A large deviation approach to some transportation cost inequalities
• Title not available (Why is that?)
• Title not available (Why is that?)
• Weighted Csiszár-Kullback-Pinsker inequalities and applications to transportation inequalities
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• Central limit theorems for the Wasserstein distance between the empirical and the true distributions
• Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• Matching random samples in many dimensions
• Quantitative concentration inequalities for empirical measures on non-compact spaces
• Metric entropy and the small ball problem for Gaussian measures
• Approximation, metric entropy and small ball estimates for Gaussian measures
• Mean rates of convergence of empirical measures in the Wasserstein metric
• Transport Inequalities. A Survey
• Rates of convergence for the empirical quantization error
• On the link between small ball probabilities and the quantization problem for Gaussian measures on Banach spaces
• Sharp asymptotics of the functional quantization problem for Gaussian processes.
• Functional quantization and small ball probabilities for Gaussian processes
• Sharp asymptotics of the Kolmogorov entropy for Gaussian measures

Cited In (55)

• Empirical optimal transport between different measures adapts to lower complexity
• Plugin estimation of smooth optimal transport maps
• Convergence of adapted empirical measures on \(\mathbb{R}^d\)
• Gromov-Wasserstein distances: entropic regularization, duality and sample complexity
• On concentration of the empirical measure for radial transport costs
• Sharp non-asymptotic concentration inequalities for the approximation of the invariant distribution of a diffusion
• Small ball probabilities, metric entropy and Gaussian rough paths
• Some recent developments in functional inequalities
• Title not available (Why is that?)
• On the rate of convergence in Wasserstein distance of the empirical measure
• Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation
• Rate of convergence of the Nanbu particle system for hard potentials and Maxwell molecules
• Constructive quantization: approximation by empirical measures
• Empirical measures and random walks on compact spaces in the quadratic Wasserstein metric
• Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
• Mean-field Markov decision processes with common noise and open-loop controls
• Berry-Esseen smoothing inequality for the Wasserstein metric on compact Lie groups
• On the rate of convergence of empirical measure in $\infty $-Wasserstein distance for unbounded density function
• Uniform rates of the Glivenko-Cantelli convergence and their use in approximating Bayesian inferences
• Mean rates of convergence of empirical measures in the Wasserstein metric
• Best finite constrained approximations of one-dimensional probabilities
• Behavior of the empirical Wasserstein distance in \({\mathbb R}^d\) under moment conditions
• A unifying approach to distributional limits for empirical optimal transport
• Limit distribution theory for smooth \(p\)-Wasserstein distances
• Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
• Free transport-entropy inequalities for non-convex potentials and application to concentration for random matrices
• Minimax confidence intervals for the sliced Wasserstein distance
• Convergence in Wasserstein distance for empirical measures of semilinear SPDEs
• On optimal matching of Gaussian samples
• Finer estimates on the \(2\)-dimensional matching problem
• Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
• Robust and Scalable Bayes via a Median of Subset Posterior Measures
• Limit theorems in Wasserstein distance for empirical measures of diffusion processes on Riemannian manifolds
• Asymptotics for Strassen's optimal transport problem
• McKean–Vlasov limit for interacting systems with simultaneous jumps
• Minimax estimation of smooth densities in Wasserstein distance
• Approximation rate in Wasserstein distance of probability measures on the real line by deterministic empirical measures
• Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees
• Uniform decomposition of probability measures: quantization, clustering and rate of convergence
• On Kac's chaos and related problems
• Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
• Empirical approximation to invariant measures for McKean-Vlasov processes: mean-field interaction vs self-interaction
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Estimation of Wasserstein distances in the spiked transport model
• Empirical measures: regularity is a counter-curse to dimensionality
• Inference for Empirical Wasserstein Distances on Finite Spaces
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• Wasserstein convergence for empirical measures of subordinated diffusions on Riemannian manifolds
• Quantitative propagation of chaos for mean field Markov decision process with common noise
• A McKean--Vlasov SDE and Particle System with Interaction from Reflecting Boundaries
• Optimal Matching of Random Samples and Rates of Convergence of Empirical Measures
• Wide consensus aggregation in the Wasserstein space. Application to location-scatter families
• Kac's chaos and Kac's program
• Sharp convergence rates for empirical optimal transport with smooth costs
• Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space

This page was built for publication: On the mean speed of convergence of empirical and occupation measures in Wasserstein distance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2451111)