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
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
[1]  
Allen G.I., Grosenick L., Taylor J., A Generalized Least-Square Matrix Decomposition, J. Amer. Statist. Assoc., 109, 505, pp. 145-159, (2014)
[2]  
Alquier P., Bayesian Methods for Low-Rank Matrix Estimation: Short Survey and Theoretical Study, Algorithmic Learning Theory 2013, pp. 309-323, (2013)
[3]  
Alquier P., Cottet V., Chopin N., Rousseau J., Bayesian Matrix Completion: Prior Specification, (2014)
[4]  
Alquier P., Ridgway J., Chopin N., On the Properties of Variational Approximations of Gibbs Posteriors, J. Machine Learning Res., 17, 239, pp. 1-41, (2016)
[5]  
Bishop C.M., Pattern Recognition and Machine Learning, (2006)
[6]  
J. Roy. Statist. Soc. Ser. B, 78, 5, (2016)
[7]  
Bittorf V., Recht B., Re C., Tropp J., Factoring Nonnegative Matrices with Linear Programs, Advances in Neural Information Processing Systems, pp. 1214-1222, (2012)
[8]  
Boyd S., Parikh N., Chu E., Peleato B., Eckstein J., Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers, Foundations and Trends in Machine Learning, 3, 1, pp. 1-122, (2011)
[9]  
Catoni O., A PAC-Bayesian Approach to Adaptive Classification, (2003)
[10]  
Catoni O., Statistical Learning Theory and Stochastic Optimization, (2004)