Year: 2019
Type: preprint
Abstract: We propose to learn deep undirected graphical models (i.e., MRFs) with a non-ELBO objective for which we can calculate exact gradients. In particular, we optimize a saddle-point objective deriving from the Bethe free energy approximation to the partition function. Unlike much recent work in approximate inference, the derived objective requires no sampling, and can be efficiently computed even for very expressive MRFs. We furthermore amortize this optimization with trained inference networks. Experimentally, we find that the proposed approach compares favorably with loopy belief propagation, but is faster, and it allows for attaining better held out log likelihood than other recent approximate inference schemes.
Source: arXiv (Cornell University)
Authors: Wiseman, Sam, Kim, Yoon
Institutions: Toyota Technological Institute at Chicago, Harvard University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2950995698