Signal Modeling and Classification Using a Robust Latent Space Model Based on Distributions

Authors:
S.P. Chatzis;D.I. Kosmopoulos;T.A. Varvarigou
Affiliations:
Nat. Tech. Univ. of Athens, Athens;-;-
Venue:
IEEE Transactions on Signal Processing
Year:
2008

Citing 0
Cited 10

The infinite hidden Markov random field model

IEEE Transactions on Neural Networks
A fast algorithm for robust mixtures in the presence of measurement errors

IEEE Transactions on Neural Networks
A variational Bayesian methodology for hidden Markov models utilizing Student's-t mixtures

Pattern Recognition
Variational Bayesian mixture of robust CCA models

ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III
A sparse nonparametric hierarchical Bayesian approach towards inductive transfer for preference modeling

Expert Systems with Applications: An International Journal
A nonparametric Bayesian approach toward robot learning by demonstration

Robotics and Autonomous Systems
The infinite Student's t-factor mixture analyzer for robust clustering and classification

Pattern Recognition
A spatially-constrained normalized Gamma process prior

Expert Systems with Applications: An International Journal
A Markov random field-regulated Pitman-Yor process prior for spatially constrained data clustering

Pattern Recognition
Nonparametric bayesian multitask collaborative filtering

Proceedings of the 22nd ACM international conference on Conference on information & knowledge management

Quantified Score

Hi-index	35.69

Visualization

Abstract

Factor analysis is a statistical covariance modeling technique based on the assumption of normally distributed data. A mixture of factor analyzers can be hence viewed as a special case of Gaussian (normal) mixture models providing a mathematically sound framework for attribute space dimensionality reduction. A significant shortcoming of mixtures of factor analyzers is the vulnerability of normal distributions to outliers. Recently, the replacement of normal distributions with the heavier-tailed Student's-t distributions has been proposed as a way to mitigate these shortcomings and the treatment of the resulting model under an expectation-maximization (EM) algorithm framework has been conducted. In this paper, we develop a Bayesian approach to factor analysis modeling based on Student's-t distributions. We derive a tractable variational inference algorithm for this model by expressing the Student's-t distributed factor analyzers as a marginalization over additional latent variables. Our innovative approach provides an efficient and more robust alternative to EM-based methods, resolving their singularity and overfitting proneness problems, while allowing for the automatic determination of the optimal model size. We demonstrate the superiority of the proposed model over well-known covariance modeling techniques in a wide range of signal processing applications.