Loop Calculus For Nonbinary Alphabets Using Concepts From Information Geometry

DOI10.1109/TIT.2015.2403239MaRDI QIDQ2978692zbMATH OpenFDO

Authors Ryuhei Mori

Publication date 28 April 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1309.6550

Mathematics Subject Classification ID

Information theory (general) (94A15) Applications of graph theory to circuits and networks (94C15)

Abstract: The Bethe approximation is a well-known approximation of the partition function used in statistical physics. Recently, an equality relating the partition function and its Bethe approximation was obtained for graphical models with binary variables by Chertkov and Chernyak. In this equality, the multiplicative error in the Bethe approximation is represented as a weighted sum over all generalized loops in the graphical model. In this paper, the equality is generalized to graphical models with non-binary alphabet using concepts from information geometry.

Cited in

(3)

• Optimal segmentation of directed graph and the minimum number of feedback arcs
• On one-step replica symmetry breaking in the Edwards-Anderson spin glass model
• Gauges, loops, and polynomials for partition functions of graphical models

This page was built for publication: Loop Calculus For Nonbinary Alphabets Using Concepts From Information Geometry

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2978692)