Algorithms for Learning Decomposable Models and Chordal Graphs
Luis de Campos, Juan Huete
Decomposable dependency models and their graphical counterparts, i.e., chordal graphs, possess a number of interesting and useful properties. On the basis of two characterizations of decomposable models in terms of independence relationships, we develop an exact algorithm for recovering the chordal graphical representation of any given decomposable model. We also propose an algorithm for learning chordal approximations of dependency models isomorphic to general undirected graphs.
Keywords: Learning, decomposable models, chordal graphs, independence.
PS Link: ftp://decsai.ugr.es/pub/utai/tech_rep/jhg/uai97.ps.Z
PDF Link: /papers/97/p46-de_campos.pdf
AUTHOR = "Luis de Campos
and Juan Huete",
TITLE = "Algorithms for Learning Decomposable Models and Chordal Graphs",
BOOKTITLE = "Proceedings of the Thirteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-97)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "1997",
PAGES = "46--53"