Nonparametric factor analysis with beta process priors

John Paisley, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

188 Scopus citations

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 digits and HGDP-CEPH cell line panel datasets.
Original languageEnglish (US)
Title of host publicationProceedings of the 26th International Conference On Machine Learning, ICML 2009
Pages777-784
Number of pages8
DOIs
StatePublished - Dec 9 2009
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2021-02-09

Fingerprint

Dive into the research topics of 'Nonparametric factor analysis with beta process priors'. Together they form a unique fingerprint.

Cite this