New approach to greedy vector quantization - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

New approach to greedy vector quantization

Résumé

We extend some rate of convergence results of greedy quantization sequences already investigated in [16]. We show, for a more general class of distributions satisfying a certain control, that the quantization error of these sequences have an n − 1 d rate of convergence and that the distortion mis-match property is satisfied. We will give some non-asymptotic Pierce type estimates. The recursive character of greedy vector quantization allows some improvements to the algorithm of computation of these sequences and the implementation of a recursive formula to quantization-based numerical integration. Furthermore, we establish further properties of sub-optimality of greedy quantization sequences.
Fichier principal
Vignette du fichier
Newgreedy_ElNmeirLushgyPages.pdf (839.61 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02529446 , version 1 (02-04-2020)

Identifiants

  • HAL Id : hal-02529446 , version 1

Citer

Rancy El Nmeir, Harald Luschgy, Gilles Pagès. New approach to greedy vector quantization. 2020. ⟨hal-02529446⟩
81 Consultations
74 Téléchargements

Partager

Gmail Facebook X LinkedIn More