Variational Inference for Stick-Breaking Beta Process Priors
Author(s): Paisley, John; Carin, Lawrence; Blei, David
DownloadTo refer to this page use:
http://arks.princeton.edu/ark:/88435/pr1wr9r
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Paisley, John | - |
dc.contributor.author | Carin, Lawrence | - |
dc.contributor.author | Blei, David | - |
dc.date.accessioned | 2021-10-08T19:50:20Z | - |
dc.date.available | 2021-10-08T19:50:20Z | - |
dc.date.issued | 2011 | en_US |
dc.identifier.citation | Paisley, John, Lawrence Carin, and David Blei. "Variational Inference for Stick-Breaking Beta Process Priors." Proceedings of the 28th International Conference on Machine Learning (2011). | en_US |
dc.identifier.uri | https://icml.cc/2011/papers/475_icmlpaper.pdf | - |
dc.identifier.uri | http://arks.princeton.edu/ark:/88435/pr1wr9r | - |
dc.description.abstract | We present a variational Bayesian inference algorithm for the stick-breaking construction of the beta process. We derive an alternate representation of the beta process that is amenable to variational inference, and present a bound relating the truncated beta process to its infinite counterpart. We assess performance on two matrix factorization problems, using a non-negative factorization model and a linearGaussian model. | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartof | Proceedings of the 28th International Conference on Machine Learning | en_US |
dc.rights | Final published version. Article is made available in OAR by the publisher's permission or policy. | en_US |
dc.title | Variational Inference for Stick-Breaking Beta Process Priors | en_US |
dc.type | Conference Article | en_US |
pu.type.symplectic | http://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceeding | en_US |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
VariationalInferenceStickBreakingBetaProcessPriors.pdf | 606.66 kB | Adobe PDF | View/Download |
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.