Fast rates for empirical vector quantization
Résumé
We consider the rate of convergence of the expected loss of empirically optimal vector quantizers. Earlier results show that the mean-squared expected distortion for any fixed distribution supported on a bounded set and satisfying some regularity conditions decreases at the rate O(log n/n). We prove that this rate is actually O(1/n). Although these conditions are hard to check, we show that well-polarized distributions with continuous densities supported on a bounded set are included in the scope of this result.
Fichier principal
Fast-rates-for-empirical-vector-quantization.pdf (270.91 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)