Open Access
May 2020 Characterization of probability distribution convergence in Wasserstein distance by $L^{p}$-quantization error function
Yating Liu, Gilles Pagès
Bernoulli 26(2): 1171-1204 (May 2020). DOI: 10.3150/19-BEJ1146

Abstract

We establish conditions to characterize probability measures by their $L^{p}$-quantization error functions in both $\mathbb{R}^{d}$ and Hilbert settings. This characterization is two-fold: static (identity of two distributions) and dynamic (convergence for the $L^{p}$-Wasserstein distance). We first propose a criterion on the quantization level $N$, valid for any norm on $\mathbb{R}^{d}$ and any order $p$ based on a geometrical approach involving the Voronoï diagram. Then, we prove that in the $L^{2}$-case on a (separable) Hilbert space, the condition on the level $N$ can be reduced to $N=2$, which is optimal. More quantization based characterization cases in dimension 1 and a discussion of the completeness of a distance defined by the quantization error function can be found at the end of this paper.

Citation

Download Citation

Yating Liu. Gilles Pagès. "Characterization of probability distribution convergence in Wasserstein distance by $L^{p}$-quantization error function." Bernoulli 26 (2) 1171 - 1204, May 2020. https://doi.org/10.3150/19-BEJ1146

Information

Received: 1 June 2018; Revised: 1 July 2019; Published: May 2020
First available in Project Euclid: 31 January 2020

zbMATH: 07166560
MathSciNet: MR4058364
Digital Object Identifier: 10.3150/19-BEJ1146

Keywords: probability distribution characterization , Vector quantization , Voronoï diagram , Wasserstein convergence

Rights: Copyright © 2020 Bernoulli Society for Mathematical Statistics and Probability

Vol.26 • No. 2 • May 2020
Back to Top