Characterization of probability distribution convergence in Wasserstein distance by L^p-quantization error function

DOI10.3150/19-BEJ1146MaRDI QIDQ2295030zbMATH OpenFDO

Authors Yating Liu, Gilles Pagès

Publication date 12 February 2020

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1801.06148, https://projecteuclid.org/euclid.bj/1580461576

zbMATH Keywords

probability distribution characterizationvector quantizationVoronoï diagramWasserstein convergence

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Probability theory on linear topological spaces (60B11) Limit theorems for vector-valued random variables (infinite-dimensional case) (60B12)

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 Vorono"i 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 on dimension 1 and a discussion of the completeness of a distance defined by the quantization error function can be found in the end of this paper.

Recommendations

• Constructive quantization: approximation by empirical measures
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Quantization for probability measures in the Prokhorov metric
• Convergence rate of optimal quantization and application to the clustering performance of the empirical measure
• On the mean speed of convergence of empirical and occupation measures in Wasserstein distance

Cites work

• A quantization algorithm for solving multidimensional discrete-time optimal stopping problems
• A QUANTIZATION TREE METHOD FOR PRICING AND HEDGING MULTIDIMENSIONAL AMERICAN OPTIONS
• A space quantization method for numerical integration
• Classical Fourier analysis
• Compactness and Tightness in a Space of Measures with the Topology of Weak Convergence.
• Exponential rate of convergence for Lloyd's method I
• Foundations of quantization for probability distributions
• Functional quantization of Gaussian processes
• Gluing lemmas and Skorohod representations
• scientific article; zbMATH DE number 3882664 (Why is no real title available?)
• scientific article; zbMATH DE number 467196 (Why is no real title available?)
• scientific article; zbMATH DE number 1022519 (Why is no real title available?)
• scientific article; zbMATH DE number 1909499 (Why is no real title available?)
• Improved error bounds for quantization based numerical schemes for BSDE and nonlinear filtering
• Introduction to vector quantization and its applications for numerics
• Optimal quadratic quantization for numerics: the Gaussian case
• Optimal Transport
• Pointwise convergence of the Lloyd I algorithm in higher dimension
• Separability and completeness for the Wasserstein distance
• The strong law of large numbers for k-means and best possible nets of Banach valued random variables
• Theoretical foundations of functional data analysis, with an introduction to linear operators

Cited in

(3)

• The Wasserstein distances between pushed-forward measures with applications to uncertainty quantification
• A semi-supervised learning approach for variance reduction in life insurance
• Distribution function estimates by Wasserstein metric and Bernstein approximation for \(C^{-1}\) functions

This page was built for publication: Characterization of probability distribution convergence in Wasserstein distance by \(L^p\)-quantization error function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2295030)