Email this article An oracle inequality for quasi-Bayesian nonnegative matrix factorization
- Authors: Alquier P.1, Guedj B.2
-
Affiliations:
- CREST, ENSAE
- Modal Project-Team
- Issue: Vol 26, No 1 (2017)
- Pages: 55-67
- Section: Article
- URL: https://journal-vniispk.ru/1066-5307/article/view/225781
- DOI: https://doi.org/10.3103/S1066530717010045
- ID: 225781
Cite item
Open Access
Access granted
Subscription Access
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.
About the authors
P. Alquier
CREST, ENSAE
Author for correspondence.
Email: pierre.alquier@ensae.fr
France, Paris
B. Guedj
Modal Project-Team
Email: pierre.alquier@ensae.fr
France, Paris
Supplementary files
