Expectation Consistent Approximate Inference: Generalizations and Convergence
Information Theory
2017-01-26 v2 math.IT
Machine Learning
Abstract
Approximations of loopy belief propagation, including expectation propagation and approximate message passing, have attracted considerable attention for probabilistic inference problems. This paper proposes and analyzes a generalization of Opper and Winther's expectation consistent (EC) approximate inference method. The proposed method, called Generalized Expectation Consistency (GEC), can be applied to both maximum a posteriori (MAP) and minimum mean squared error (MMSE) estimation. Here we characterize its fixed points, convergence, and performance relative to the replica prediction of optimality.
Cite
@article{arxiv.1602.07795,
title = {Expectation Consistent Approximate Inference: Generalizations and Convergence},
author = {Alyson K. Fletcher and Mojtaba Sahraee-Ardakan and Sundeep Rangan and Philip Schniter},
journal= {arXiv preprint arXiv:1602.07795},
year = {2017}
}
Comments
10 pages