Work

Expectation consistent approximate inference: Generalizations and convergence

Year: 2016

Type: conference-paper

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.

Source: IEEE International Symposium on Information Theory (ISIT)

DOI: 10.1109/isit.2016.7541287

Authors: Alyson Fletcher, Mojtaba Sahraee-Ardakan, Sundeep Rangan, Philip Schniter

Institutions: University of California, Los Angeles, University City Science Center, University of California, Santa Cruz, New York University, The Ohio State University

Language: English

Topic: Bayesian Modeling and Causal Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Ohio State University, Office of Naval Research