The max-min hill-climbing bayesian network structure learning algorithm

The max-min hill-climbing bayesian network structure learning algorithm (2006)

Cached

Download Links

[discover.mc.vanderbilt.edu]

Other Repositories/Bibliography

DBLP

by Ioannis Tsamardinos , Laura E. Brown , Constantin F. Aliferis

Venue:	Machine Learning
Citations:	39 - 3 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	The max-min hill-climbing bayesian network structure learning algorithm	INFERENCE
AUTHOR NAME	Ioannis Tsamardinos	SVM HeaderParse 0.2
AUTHOR NAME	Laura E. Brown	SVM HeaderParse 0.2
AUTHOR NAME	Constantin F. Aliferis	SVM HeaderParse 0.2
AUTHOR AFFIL	Discovery Systems Laboratory,; Dept. of Biomedical Informatics; Vanderbilt University	SVM HeaderParse 0.2
AUTHOR ADDR	2209 Garland Avenue; Nashville, TN 37232-8340	SVM HeaderParse 0.2
ABSTRACT	Abstract. We present a new algorithm for Bayesian network structure learning, called Max-Min Hill-Climbing (MMHC). The algorithm combines ideas from local learning, constraint-based, and search-and-score techniques in a principled and effective way. It first reconstructs the skeleton of a Bayesian network and then performs a Bayesian-scoring greedy hill-climbing search to orient the edges. In our extensive empirical evaluation MMHC outperforms on average and in terms of various metrics several prototypical and state-of-the-art algorithms, namely the PC, Sparse Candidate, Three Phase Dependency Analysis, Optimal Reinsertion, Greedy Equivalence Search, and Greedy Search. These are the first empirical results simultaneously comparing most of the major Bayesian network algorithms against each other. MMHC offers certain theoretical advantages, specifically over the Sparse Candidate algorithm, corroborated by our experiments. MMHC and detailed results of our study are publicly available at	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	Machine Learning	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	2006	INFERENCE
VOLUME	65	INFERENCE
CITATIONS	73 found	ParsCit 1.0