Potential approach in marginalizing Gibbs models

Citation
E. Castillo et al., Potential approach in marginalizing Gibbs models, INT J APPRO, 21(3), 1999, pp. 257-290
Citations number
38
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING
ISSN journal
0888613X → ACNP
Volume
21
Issue
3
Year of publication
1999
Pages
257 - 290
Database
ISI
SICI code
0888-613X(199908)21:3<257:PAIMGM>2.0.ZU;2-C
Abstract
Given an undirected graph G or hypergraph potential H model for a given set of variables V, we introduce two marginalization operators for obtaining t he undirected graph G(A) or hypergraph H-A associated with a given subset A subset of V such that the marginal distribution of A factorizes according to G(A) or H-A, respectively. Finally, we illustrate the method by its appl ication to some practical examples. With them we show that potential approa ch allow defining a finer factorization or performing a more precise condit ional independence analysis than undirected graph models. Finally, we expla in connections with related works. (C) 1999 Elsevier Science Inc. All right s reserved.