Asymptotics for Optimal Empirical Quantization of Measures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Quattrocchi, Filippo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910574813642752
author Quattrocchi, Filippo
author_facet Quattrocchi, Filippo
contents We investigate the minimal error in approximating a general probability measure $μ$ on $\mathbb{R}^d$ by the uniform measure on a finite set with prescribed cardinality $n$. The error is measured in the $p$-Wasserstein distance. In particular, when $1\le p<d$, we establish asymptotic upper and lower bounds as $n \to \infty$ on the rescaled minimal error that have the same, explicit dependency on $μ$. In some instances, we prove that the rescaled minimal error has a limit. These include general measures in dimension $d = 2$ with $1 \le p < 2$, and uniform measures in arbitrary dimension with $1 \le p < d$. For some uniform measures, we prove the limit existence for $p \ge d$ as well. For a class of compactly supported measures with Hölder densities, we determine the convergence speed of the minimal error for every $p \ge 1$. Furthermore, we establish a new Pierce-type (i.e., nonasymptotic) upper estimate of the minimal error when $1 \le p < d$. In the initial sections, we survey the state of the art and draw connections with similar problems, such as classical and random quantization.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12924
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Asymptotics for Optimal Empirical Quantization of Measures
Quattrocchi, Filippo
Probability
Optimization and Control
41A25 (Primary), 62E17, 49Q22
We investigate the minimal error in approximating a general probability measure $μ$ on $\mathbb{R}^d$ by the uniform measure on a finite set with prescribed cardinality $n$. The error is measured in the $p$-Wasserstein distance. In particular, when $1\le p<d$, we establish asymptotic upper and lower bounds as $n \to \infty$ on the rescaled minimal error that have the same, explicit dependency on $μ$. In some instances, we prove that the rescaled minimal error has a limit. These include general measures in dimension $d = 2$ with $1 \le p < 2$, and uniform measures in arbitrary dimension with $1 \le p < d$. For some uniform measures, we prove the limit existence for $p \ge d$ as well. For a class of compactly supported measures with Hölder densities, we determine the convergence speed of the minimal error for every $p \ge 1$. Furthermore, we establish a new Pierce-type (i.e., nonasymptotic) upper estimate of the minimal error when $1 \le p < d$. In the initial sections, we survey the state of the art and draw connections with similar problems, such as classical and random quantization.
title Asymptotics for Optimal Empirical Quantization of Measures
topic Probability
Optimization and Control
41A25 (Primary), 62E17, 49Q22
url https://arxiv.org/abs/2408.12924