A Sharp Oracle Inequality for Bayesian Non-Negative Matrix Factorization - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

A Sharp Oracle Inequality for Bayesian Non-Negative Matrix Factorization

Résumé

The aim of this paper is to provide some theoretical understanding of Bayesian non-negative matrix factorization methods. We prove a sharp oracle inequality for a quasi-Bayesian estimator. This result holds for a very general class of prior distributions and shows how the prior affects the rate of convergence. We illustrate our theoretical results with a short numerical study along with a discussion on existing implementations .
Fichier principal
Vignette du fichier
main.pdf (272.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01251878 , version 1 (06-01-2016)
hal-01251878 , version 2 (07-06-2016)
hal-01251878 , version 3 (25-08-2016)
hal-01251878 , version 4 (26-06-2018)

Identifiants

  • HAL Id : hal-01251878 , version 2

Citer

Pierre Alquier, Benjamin Guedj. A Sharp Oracle Inequality for Bayesian Non-Negative Matrix Factorization. 2016. ⟨hal-01251878v2⟩
1657 Consultations
826 Téléchargements

Partager

Gmail Facebook X LinkedIn More