Mean-field methods for a special class of Belief Networks

Bhattacharyya, Chiranjib and Keerthi, Sathiya S (2001) Mean-field methods for a special class of Belief Networks. In: Journal Of Artificial Intelligence Research, 15 . pp. 91-114.

PDF Mean.pdf - Published Version Restricted to Registered users only Download (298kB) | Request a copy

Abstract

The chief aim of this paper is to propose mean-field approximations for a broad class of Belief networks, of which sigmoid and noisy-or networks can be seen as special cases. The approximations are based on a powerful mean-field theory suggested by Plefka. We show that Saul, Jaakkola, and Jordan's approach is the first order approximation in Plefka's approach, via a variational derivation. The application of Plefka's theory to belief networks is not computationally tractable. To tackle this problem we propose new approximations based on Taylor series. Small scale experiements show that the proposed schemes are attractive.

Item Type:	Journal Article
Publication:	Journal Of Artificial Intelligence Research
Publisher:	AI Access Foundation and Morgan Kaufmann
Additional Information:	Copyright of this article belongs to AI Access Foundation and Morgan Kaufmann.
Keywords:	Distributions;Information;Algorithm;Model
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	10 Feb 2010 06:45
Last Modified:	19 Sep 2010 04:55
URI:	http://eprints.iisc.ac.in/id/eprint/17140

Actions (login required)

View Item