Nonparametric factor analysis with beta process priors

Abstract

We propose a nonparametric extension to the factor analysis problem using a beta process prior. This <i>beta process factor analysis</i> (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… (More)
DOI: 10.1145/1553374.1553474

Topics

8 Figures and Tables

Statistics

02040'07'08'09'10'11'12'13'14'15'16'17'18
Citations per Year

241 Citations

Semantic Scholar estimates that this publication has 241 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Paisley2009NonparametricFA, title={Nonparametric factor analysis with beta process priors}, author={John William Paisley and Lawrence Carin}, booktitle={ICML}, year={2009} }