Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Variational Message Passing with Structured Inference Networks
Wu Lin, Nicolas Hubacher, Mohammad Emtiyaz Khan
Feb 15, 2018 (modified: Feb 23, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Recent efforts on combining deep models with probabilistic graphical models are promising in providing flexible models that are also easy to interpret. We propose a variational message-passing algorithm for variational inference in such models. We make three contributions. First, we propose structured inference networks that incorporate the structure of the graphical model in the inference network of variational auto-encoders (VAE). Second, we establish conditions under which such inference networks enable fast amortized inference similar to VAE. Finally, we derive a variational message passing algorithm to perform efficient natural-gradient inference while retaining the efficiency of the amortized inference. By simultaneously enabling structured, amortized, and natural-gradient inference for deep structured models, our method simplifies and generalizes existing methods.
TL;DR:We propose a variational message-passing algorithm for models that contain both the deep model and probabilistic graphical model.