An oracle inequality for quasi-Bayesian nonnegative matrix factorization

被引：9
作者：
Alquier P. [1 ]
Guedj B. [2 ]
机构：
[1] CREST, ENSAE, Univ. Paris Saclay, Paris
[2] Modal Project-Team, Inria Lille – Nord Europe Research Center, Paris
来源：
Mathematical Methods of Statistics | 2017年 / 26卷 / 1期
关键词：
nonnegative matrix factorization; oracle inequality; PAC-Bayesian bounds;
D O I：
10.3103/S1066530717010045
中图分类号：
学科分类号：
摘要：
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. © 2017, Allerton Press, Inc.
引用
收藏
页码：55 / 67
页数：12
相关论文
共 50 条
[31]  
Li L., Guedj B., Loustau S., PAC-Bayesian Online Clustering, (2016)
[32]  
Lim Y.J., Teh Y.W., Variational Bayesian Approach to Movie Rating Prediction, Proc. KDD Cup and Workshop, 7, pp. 5-21, (2007)
[33]  
Lin C.-J., Projected Gradient Methods for Nonnegative Matrix Factorization, Neural Computation, 19, 10, pp. 2756-2779, (2007)
[34]  
MacKay D.J.C., Information Theory, Inference and Learning Algorithms, (2002)
[35]  
Mai T.T., Alquier P., A Bayesian Approach for Matrix Completion: Optimal Rates under General Sampling Distributions, Electronic J. Statist., 9, pp. 823-841, (2015)
[36]  
McAllester D., Some PAC-Bayesian Theorems, Proc. 11th Annual Conf. on Comput. Learning Theory, pp. 230-234, (1998)
[37]  
Moussaoui S., Brie D., Mohammad-Djafari A., Carteret C., Separation of Nonnegative Mixture of Nonnegative Sources Using a Bayesian Approach and MCMC Sampling, IEEE Trans. on Signal Processing, 54, 11, pp. 4133-4145, (2006)
[38]  
Ozerov A., Fevotte C., Multichannel Nonnegative Matrix Factorization in Convolutive Mixtures for Audio Source Separation, IEEE Trans. on Audio, Speech, and Language Processing, 18, 3, pp. 550-563, (2010)
[39]  
Paisley J., Blei D., Jordan M.I., Bayesian Nonnegative Matrix Factorization with Stochastic Variational Inference, Handbook of Mixed Membership Models and Their Applications, (2015)
[40]  
Salakhutdinov R., Mnih A., Bayesian Probabilistic Matrix Factorization Using Markov Chain Monte Carlo, Proc. 25th Internat. Conf. on Machine Learning, pp. 880-887, (2008)
12345