Table of Contents
Fetching ...

Convergence rates for the $p$-Wasserstein distance of the empirical measures of an ergodic Markov process

René L. Schilling, Jian Wang, Bingyao Wu, Jie-Xiang Zhu

Abstract

Let $X:=(X_t)_{t\geq 0}$ be an ergodic Markov process on $\real^d$, and $p>0$. We derive upper bounds of the $p$-Wasserstein distance between the invariant measure and the empirical measures of the Markov process $X$. For this we assume, e.g.\ that the transition semigroup of $X$ is exponentially contractive in terms of the $1$-Wasserstein distance, or that the iterated Poincaré inequality holds together with certain moment conditions on the invariant measure. Typical examples include diffusions and underdamped Langevin dynamics.

Convergence rates for the $p$-Wasserstein distance of the empirical measures of an ergodic Markov process

Abstract

Let be an ergodic Markov process on , and . We derive upper bounds of the -Wasserstein distance between the invariant measure and the empirical measures of the Markov process . For this we assume, e.g.\ that the transition semigroup of is exponentially contractive in terms of the -Wasserstein distance, or that the iterated Poincaré inequality holds together with certain moment conditions on the invariant measure. Typical examples include diffusions and underdamped Langevin dynamics.
Paper Structure (11 sections, 9 theorems, 156 equations)

This paper contains 11 sections, 9 theorems, 156 equations.

Key Result

Theorem 1.1

Let $(X_t)_{t\geq 0}$ be an ergodic Markov process on ${\mathds R}^d$ with invariant measure $\mu$. Assume that (H1) holds, let $p>0$, and assume that $\mu$ has for some $q> \max\{p, 1\}$ a $q$-th moment $\mu(|\cdot|^q) <\infty.$ Define Then there exists a constant $C>0$ such that for all $T \ge 2$,

Theorems & Definitions (13)

  • Theorem 1.1
  • Theorem 1.2
  • Theorem 1.3
  • Theorem 1.4
  • Theorem 2.1
  • Lemma 2.2
  • Lemma 3.1
  • proof
  • Example 5.1
  • proof
  • ...and 3 more