PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Linearly constrained Bayesian matrix factorization for blind source separation
Mikkel N. Schmidt
In: Neural Information Processing Systems, Advances in (NIPS), 2009(2009).

Abstract

Abstract: We present a general Bayesian approach to probabilistic matrix factorization subject to linear constraints. The approach is based on a Gaussian observation model and Gaussian priors with bilinear equality and inequality constraints. We present an efficient Markov chain Monte Carlo inference procedure based on Gibbs sampling. Special cases of the proposed model are Bayesian formulations of non-negative matrix factorization and factor analysis. The method is evaluated on a blind source separation problem. We demonstrate that our algorithm can be used to extract meaningful and interpretable features that are remarkably different from features extracted using existing related matrix factorization techniques.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:6528
Deposited By:Mikkel Schmidt
Deposited On:08 March 2010