ORBi: Auvray Vincent - Learning inclusion-optimal chordal graphs

Reference : Learning inclusion-optimal chordal graphs


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/34055

Title :	Learning inclusion-optimal chordal graphs
Language :	English
Author, co-author :	Auvray, Vincent [Université de Liège - ULG > Département d'électricité, électronique et informatique - Systèmes et Modélisation > > >]
	Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Publication date :	9-Jul-2008
Main document title :	Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence (UAI-08)
Publisher :	Morgan Kaufmann
Pages :	18–25
On invitation :	No
Audience :	International
Event name :	24th Conference on Uncertainty in Artificial Intelligence (UAI-08)
Event date :	from 9-7-2008 to 12-7-2008
Event place (city) :	Helsinki
Event country :	Finland
Keywords :	[en] Machine Learning ; Graphical Models
Abstract :	[en] Chordal graphs can be used to encode dependency models that are representable by both directed acyclic and undirected graphs. This paper discusses a very simple and efficient algorithm to learn the chordal structure of a probabilistic model from data. The algorithm is a greedy hill-climbing search algorithm that uses the inclusion boundary neighborhood over chordal graphs. In the limit of a large sample size and under appropriate hypotheses on the scoring criterion, we prove that the algorithm will find a structure that is inclusion-optimal when the dependency model of the data-generating distribution can be represented exactly by an undirected graph. The algorithm is evaluated on simulated datasets.
Research units :	Giga-Systems Biology and Chemical Biology
Name of the research project :	BIOMOD ARC
Target :	Researchers ; Professionals ; Students
Permalink :	http://hdl.handle.net/2268/34055

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	auvray.pdf		Author postprint	186.12 kB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5