On some provably correct cases of variational inference for topic models

Pranjal Awasthi, Andrej Risteski

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations


Variational inference is an efficient, popular heuristic used in the context of latent variable models. We provide the first analysis of instances where variational inference algorithms converge to the global optimum, in the setting of topic models. Our initializations are natural, one of them being used in LDA-c, the most popular implementation of variational inference. In addition to providing intuition into why this heuristic might work in practice, the multiplicative, rather than additive nature of the variational inference updates forces us to use non-standard proof arguments, which we believe might be of general theoretical interest.

Original languageEnglish (US)
Pages (from-to)2098-2106
Number of pages9
JournalAdvances in Neural Information Processing Systems
StatePublished - 2015
Event29th Annual Conference on Neural Information Processing Systems, NIPS 2015 - Montreal, Canada
Duration: Dec 7 2015Dec 12 2015

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this