Affordable Access

Access to the full text

An oracle inequality for quasi-Bayesian nonnegative matrix factorization

Authors
  • Alquier, P.1
  • Guedj, B.2
  • 1 Univ. Paris Saclay, CREST, ENSAE, Paris, France , Paris (France)
  • 2 Inria Lille – Nord Europe Research Center, Modal Project-Team, Paris, France , Paris (France)
Type
Published Article
Journal
Mathematical Methods of Statistics
Publisher
Allerton Press
Publication Date
Jan 01, 2017
Volume
26
Issue
1
Pages
55–67
Identifiers
DOI: 10.3103/S1066530717010045
Source
Springer Nature
Keywords
License
Yellow

Abstract

The aim of this paper is to provide some theoretical understanding of quasi-Bayesian aggregation methods of nonnegative matrix factorization. We derive an oracle inequality for an aggregated estimator. This result holds for a very general class of prior distributions and shows how the prior affects the rate of convergence.

Report this publication

Statistics

Seen <100 times