Region-based Energy Neural Network for Approximate Inference

06/17/2020
by   Dong Liu, et al.
4

Region-based free energy was originally proposed for generalized belief propagation (GBP) to improve loopy belief propagation (loopy BP). In this paper, we propose a neural network based energy model for inference in general Markov random fields (MRFs), which directly minimizes the region-based free energy defined on region graphs. We term our model Region-based Energy Neural Network (RENN). Unlike message-passing algorithms, RENN avoids iterative message propagation and is faster. Also different from recent deep neural network based models, inference by RENN does not require sampling, and RENN works on general MRFs. RENN can also be employed for MRF learning. Our experiments on marginal distribution estimation, partition function estimation, and learning of MRFs show that RENN outperforms the mean field method, loopy BP, GBP, and the state-of-the-art neural network based model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/02/2011

Merging Belief Propagation and the Mean Field Approximation: A Free Energy Approach

We present a joint message passing approach that combines belief propaga...
research
01/28/2022

Regionalized optimization

Yedidia, Freeman, Weiss have shown in their reference article, "Construc...
research
05/24/2019

Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay

Belief propagation is a fundamental message-passing algorithm for probab...
research
03/16/2015

Statistical Analysis of Loopy Belief Propagation in Random Fields

Loopy belief propagation (LBP), which is equivalent to the Bethe approxi...
research
06/14/2019

Amortized Bethe Free Energy Minimization for Learning MRFs

We propose to learn deep undirected graphical models (i.e., MRFs), with ...
research
09/24/2020

Message-Passing Algorithms and Homology

This PhD thesis lays out algebraic and topological structures relevant f...
research
12/01/2017

Susceptibility Propagation by Using Diagonal Consistency

A susceptibility propagation that is constructed by combining a belief p...

Please sign up or login with your details

Forgot password? Click here to reset