Discriminative learning of Bayesian networks via factorized conditional log-likelihood

Show full item record



Permalink

http://hdl.handle.net/10138/28459

Citation

Carvalho , A M , Roos , T T , Oliveira , A L & Myllymäki , P 2011 , ' Discriminative learning of Bayesian networks via factorized conditional log-likelihood ' , Journal of Machine Learning Research , vol. 12 , pp. 2181-2210 . < http://jmlr.csail.mit.edu/papers/v12/carvalho11a.html >

Title: Discriminative learning of Bayesian networks via factorized conditional log-likelihood
Author: Carvalho, Alexandra M.; Roos, Teemu Teppo; Oliveira, Arlindo L.; Myllymäki, Petri
Contributor: University of Helsinki, Helsinki Institute for Information Technology
University of Helsinki, Helsinki Institute for Information Technology
Date: 2011
Language: eng
Number of pages: 30
Belongs to series: Journal of Machine Learning Research
ISSN: 1532-4435
URI: http://hdl.handle.net/10138/28459
Abstract: We propose an efficient and parameter-free scoring criterion, the factorized conditional log-likelihood (ˆfCLL), for learning Bayesian network classifiers. The proposed score is an approximation of the conditional log-likelihood criterion. The approximation is devised in order to guarantee decomposability over the network structure, as well as efficient estimation of the optimal parameters, achieving the same time and space complexity as the traditional log-likelihood scoring criterion. The resulting criterion has an information-theoretic interpretation based on interaction information, which exhibits its discriminative nature. To evaluate the performance of the proposed criterion, we present an empirical comparison with state-of-the-art classifiers. Results on a large suite of benchmark data sets from the UCI repository show that ˆfCLL-trained classifiers achieve at least as good accuracy as the best compared classifiers, using significantly less computational resources.
Subject: 113 Computer and information sciences
112 Statistics and probability
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
carvalho11a.pdf 436.6Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record