Provable algorithms for inference in topic models

Recently, 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...

Full description

Bibliographic Details
Main Authors: Arora, Sanjeev, Ge, Rong, Ma, Tengyu, Koehler, Frederic, Moitra, Ankur
Other Authors: Massachusetts Institute of Technology. Department of Mathematics
Format: Article
Published: PMLR 2018
Online Access:http://hdl.handle.net/1721.1/115942
https://orcid.org/0000-0001-7047-0495