Loop Calculus For Nonbinary Alphabets Using Concepts From Information Geometry

descriptionPublicationkeyboard_double_arrow_right Article , Preprint 01 Apr 2015Embargo end date: 01 Jan 2013 Japan Publisher:Institute of Electrical and Electronics Engineers (IEEE)Journal:IEEE Transactions on Information Theory, volume 61, pages 1,887-1,904 (issn: 0018-9448, eissn: 1557-9654,

Copyright policy )

Authors: Ryuhei Mori;

doi: 10.1109/tit.2015.2403239 , 10.48550/arxiv.1309.6550

arXiv: 1309.6550

Loop Calculus For Nonbinary Alphabets Using Concepts From Information Geometry

- Summary
- Subjects
- Metrics

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.

18 pages, 4 figures, submitted to IEEE Trans. Inf. Theory

Country

Japan

Related Organizations

Institute of Science Tokyo
Japan

Keywords

FOS: Computer and information sciences, 570, Statistical Mechanics (cond-mat.stat-mech), Computer Science - Information Theory, Information Theory (cs.IT), FOS: Physical sciences, Condensed Matter - Statistical Mechanics, 004

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	8
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 10%