Nonparametric Factor Analysis with Beta Process Priors
Abstract
We propose a nonparametric extension to the factor analysis problem using a beta process prior. This beta process factor analysis (BP-FA) model allows for a dataset to be decomposed into a linear combination of a sparse set of factors, providing information on the underlying structure of the observations. As with the Dirichlet process, the beta process is a fully Bayesian conjugate prior, which allows for analytical posterior calculation and straightforward inference. We derive a variational Bayes inference algorithm and demonstrate the model on the MNIST handwritten digits and HGDP-CEPH cell line panel datasets.
Cite
Text
Paisley and Carin. "Nonparametric Factor Analysis with Beta Process Priors." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553474Markdown
[Paisley and Carin. "Nonparametric Factor Analysis with Beta Process Priors." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/paisley2009icml-nonparametric/) doi:10.1145/1553374.1553474BibTeX
@inproceedings{paisley2009icml-nonparametric,
title = {{Nonparametric Factor Analysis with Beta Process Priors}},
author = {Paisley, John W. and Carin, Lawrence},
booktitle = {International Conference on Machine Learning},
year = {2009},
pages = {777-784},
doi = {10.1145/1553374.1553474},
url = {https://mlanthology.org/icml/2009/paisley2009icml-nonparametric/}
}