DocumentCode :
2332265
Title :
A Gibbs Sampling Approach to Independent Factor Analysis
Author :
Adenle, Omolabake A. ; Fitzgerald, William J.
Author_Institution :
Dept. of Eng., Cambridge Univ.
Volume :
5
fYear :
2006
fDate :
14-19 May 2006
Abstract :
We present a Gibbs sampler for estimating parameters of the independent factor model. Independent factor analysis (IFA) is a generalization of mixtures of factor analyzers, where instead we learn nonlinear subspaces in data. IFA can also be considered a method for blind source separation. The IFA generative model is hierarchical, with each factor modeled as an independent mixture of Gaussians, each mixture component representing a factor state. Computing expectations over factors quickly becomes intractable with increasing number of factors as this requires summation over exponentially many state configurations, making parameter estimation via expectation maximization (EM) with an exact E-step infeasible. Unlike the variational method that has been proposed, we take a simulation based approach to obtain exact parameter estimates. We define prior distributions and use a Gibbs sampler to obtain samples from the parameter posterior. Application to synthetic data demonstrates effectiveness of the method in estimating model parameters and robustness to model permutation invariance
Keywords :
Gaussian processes; blind source separation; parameter estimation; sampling methods; Gibbs sampling approach; independent Gaussian mixture; independent factor analysis; Additive noise; Computational modeling; Covariance matrix; Gaussian processes; Hidden Markov models; Independent component analysis; Parameter estimation; Sampling methods; Stochastic processes; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Type :
conf
DOI :
10.1109/ICASSP.2006.1661359
Filename :
1661359
Link To Document :
بازگشت