Timezone: »
Spotlight
On some provably correct cases of variational inference for topic models
Pranjal Awasthi · Andrej Risteski
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 mostpopular 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 usenon-standard proof arguments, which we believe might be of general theoretical interest.
Author Information
Pranjal Awasthi (Princeton)
Andrej Risteski (Princeton)
More from the Same Authors
-
2016 Poster: Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods »
Andrej Risteski · Yuanzhi Li -
2016 Poster: Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates »
Yuanzhi Li · Yingyu Liang · Andrej Risteski -
2016 Poster: Algorithms and matching lower bounds for approximately-convex optimization »
Andrej Risteski · Yuanzhi Li -
2015 Poster: On some provably correct cases of variational inference for topic models »
Pranjal Awasthi · Andrej Risteski -
2014 Poster: Learning Mixtures of Ranking Models »
Pranjal Awasthi · Avrim Blum · Or Sheffet · Aravindan Vijayaraghavan -
2014 Spotlight: Learning Mixtures of Ranking Models »
Pranjal Awasthi · Avrim Blum · Or Sheffet · Aravindan Vijayaraghavan -
2010 Spotlight: Supervised Clustering »
Pranjal Awasthi · Reza Zadeh -
2010 Poster: Supervised Clustering »
Pranjal Awasthi · Reza Zadeh