Skip to main content

Provable algorithms for inference in topic models

Author(s): Arora, Sanjeev; Ge, R; Koehler, F; Ma, T; Moitra, A

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr14b19
Full metadata record
DC FieldValueLanguage
dc.contributor.authorArora, Sanjeev-
dc.contributor.authorGe, R-
dc.contributor.authorKoehler, F-
dc.contributor.authorMa, T-
dc.contributor.authorMoitra, A-
dc.date.accessioned2019-08-29T17:04:50Z-
dc.date.available2019-08-29T17:04:50Z-
dc.date.issued2016en_US
dc.identifier.citationArora, S, Ge, R, Koehler, F, Ma, T, Moitra, A. (2016). Provable algorithms for inference in topic models. 6 (4176 - 4184en_US
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr14b19-
dc.description.abstractRecently, there has been considerable progress on designing algorithms with provable guarantees - typically using linear algebraic methods - for parameter learning in latent variable models. But designing provable algorithms for inference has proven to be more challenging. Here we take a first step towards provable inference in topic models. We leverage a property of topic models that enables us to construct simple linear estimators for the unknown topic proportions that have small variance, and consequently can work with short documents. Our estimators also correspond to finding an estimate around which the posterior is well-concentrated. We show lower bounds that for shorter documents it can be information theoretically impossible to find the hidden topics. Finally, we give empirical results that demonstrate that our algorithm works on realistic topic models. It yields good solutions on synthetic data and runs in time comparable to a single iteration of Gibbs sampling.en_US
dc.format.extent4176 - 4184en_US
dc.language.isoen_USen_US
dc.relation.ispartof33rd International Conference on Machine Learningen_US
dc.rightsAuthor's manuscripten_US
dc.titleProvable algorithms for inference in topic modelsen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
Provable Algorithms for Inference in Topic Models.pdf433.28 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.