Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
From MaRDI portal
Publication:2170252
Abstract: We consider a Markov chain on with invariant measure . We are interested in the rate of convergence of the empirical measures towards the invariant measure with respect to various dual distances, including in particular the -Wasserstein distance. The main result of this article is a new upper bound for the expected distance, which is proved by combining a Fourier expansion with a truncation argument. Our bound matches the known rates for i.i.d. random variables up to logarithmic factors. In addition, we show how concentration inequalities around the mean can be obtained.
Recommendations
- On the rate of convergence in Wasserstein distance of the empirical measure
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- Subgeometric rates of convergence in Wasserstein distance for Markov chains
- Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
- Mean rates of convergence of empirical measures in the Wasserstein metric
Cites work
- \(L_1\)-quantization and clustering in Banach spaces
- L^\infty -Multivariate Approximation Theory
- Concentration of measure on product spaces with applications to Markov processes
- Constructive quantization: approximation by empirical measures
- Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
- Deviation inequalities for separately Lipschitz functionals of iterated random functions
- Empirical measures: regularity is a counter-curse to dimensionality
- Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
- Fractional Integration in Orlicz Spaces. I
- scientific article; zbMATH DE number 1246230 (Why is no real title available?)
- On optimal matchings
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- On the rate of convergence in Wasserstein distance of the empirical measure
- Optimal Transport
- Quantitative concentration inequalities for empirical measures on non-compact spaces
- Ricci curvature of Markov chains on metric spaces
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
- The Speed of Mean Glivenko-Cantelli Convergence
Cited in
(13)- Quantitative convergence rates of Markov chains: A simple account
- Wasserstein asymptotics for the empirical measure of fractional Brownian motion on a flat torus
- Curvature and transport inequalities for Markov chains in discrete spaces
- Subexponential upper and lower bounds in Wasserstein distance for Markov processes
- On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
- Subgeometric rates of convergence in Wasserstein distance for Markov chains
- Empirical measures: regularity is a counter-curse to dimensionality
- Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm
- Empirical approximation to invariant measures for McKean-Vlasov processes: mean-field interaction vs self-interaction
- Quantitative bounds for Markov chain convergence: Wasserstein and total variation distances
- Annealed quantitative estimates for the quadratic 2D-discrete random matching problem
- Empirical approximation to invariant measures of non-degenerate McKean-Vlasov dynamics
- Asymptotics of Kantorovich distance for empirical measures of the Laguerre model
This page was built for publication: Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2170252)
