PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Locally minimax optimal predictive modeling with Bayesian networks
Tomi Silander, Teemu Roos and Petri Myllymäki
In: 12th International Conference on Artificial Intelligence and Statistics, 16-18 April, 2009, Clearwater Beach, FL, USA.

Abstract

We propose an information-theoretic approach for predictive modeling with Bayesian networks. Our approach is based on the minimax optimal Normalized Maximum Likelihood (NML) distribution, motivated by the MDL principle. In particular, we present a parameter learning method which, together with a previously introduced NML-based model selection criterion, provides a way to construct highly predictive Bayesian network models from data. The method is parameter-free and robust, unlike the currently popular Bayesian marginal likelihood approach which has been shown to be sensitive to the choice of prior hyperparameters. Empirical tests show that the proposed method compares favorably with the Bayesian approach in predictive tasks.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:5168
Deposited By:Teemu Roos
Deposited On:24 March 2009