Spotlight
On some provably correct cases of variational inference for topic models
Pranjal Awasthi · Andrej Risteski

Tue Dec 8th 11:35 AM -- 12:00 PM @ Room 210 A

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