ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Generalized Belief Propagation for Estimating the Partition Function of the 2D Ising Model

Chan, Chun Lam and Siavoshani, Mahdi Jafari and Jaggi, Sidharth and Kashyap, Navin and Vontobel, Pascal O (2015) Generalized Belief Propagation for Estimating the Partition Function of the 2D Ising Model. In: IEEE International Symposium on Information Theory (ISIT), JUN 14-19, 2015, Hong Kong, PEOPLES R CHINA, pp. 2261-2265.

[img] PDF
IEEE_Int_Sym_Inf_The_2261_2015.pdf - Published Version
Restricted to Registered users only

Download (661Kb) | Request a copy
Official URL: http://dx.doi.org/10.1109/ISIT.2015.7282858

Abstract

Recent empirical results have demonstrated that generalized belief propagation (GBP) can be used to closely estimate the capacity of certain 2D runlength-limited constraints. We provide a partial analytical validation of these observations by showing that GBP yields a lower bound on the partition function of 2D Ising models with restricted grid size. While previous papers have proved that belief propagation (BP) can be used to obtain a lower bound on the partition function of 2D Ising models, this paper is the first work that analyzes GBP-based partition function approximations of 2D Ising models.

Item Type: Conference Proceedings
Related URLs:
Additional Information: Copy right for this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Department/Centre: Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited: 07 Dec 2016 05:47
Last Modified: 07 Dec 2016 05:47
URI: http://eprints.iisc.ernet.in/id/eprint/55514

Actions (login required)

View Item View Item