Zador Theorem for optimal quantization with respect to Bregman divergences

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Boutoille, Guillaume, Pagès, Gilles
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914441634775040
author Boutoille, Guillaume
Pagès, Gilles
author_facet Boutoille, Guillaume
Pagès, Gilles
contents We establish a Zador like theorem for $L^r$-optimal vector quantization when the similarity measure is a twice differentiable Bregman divergence of a strictly convex function. On our way we also prove a similar result when the Bregman divergence is replaced by a continuous matrix-valued vector field having values in the set of positive definite matrices. We adopt the strategy of the first fully rigorous proof of the original Zador' theorem (when the similarity measure is the power of a norm). We have to overcome several difficulties which are specific to this framework especially concerning the so-called firewall lemma.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02354
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zador Theorem for optimal quantization with respect to Bregman divergences
Boutoille, Guillaume
Pagès, Gilles
Functional Analysis
Probability
65C20, 65N50, 90C39, 93E35, 91B28
We establish a Zador like theorem for $L^r$-optimal vector quantization when the similarity measure is a twice differentiable Bregman divergence of a strictly convex function. On our way we also prove a similar result when the Bregman divergence is replaced by a continuous matrix-valued vector field having values in the set of positive definite matrices. We adopt the strategy of the first fully rigorous proof of the original Zador' theorem (when the similarity measure is the power of a norm). We have to overcome several difficulties which are specific to this framework especially concerning the so-called firewall lemma.
title Zador Theorem for optimal quantization with respect to Bregman divergences
topic Functional Analysis
Probability
65C20, 65N50, 90C39, 93E35, 91B28
url https://arxiv.org/abs/2604.02354