Learning Bayesian Nets that Perform Well

2013/02/06 by Greiner, Russell, Grove, Adam J., Schuurmans, Dale
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.1302.1542

Abstract

A Bayesian net (BN) is more than a succinct way to encode a probabilistic distribution; it also corresponds to a function used to answer queries. A BN can therefore be evaluated by the accuracy of the answers it returns. Many algorithms for learning BNs, however, attempt to optimize another criterion (usually likelihood, possibly augmented with a regularizing term), which is independent of the distribution of queries that are posed. This paper takes the "performance criteria" seriously, and considers the challenge of computing the BN whose performance - read "accuracy over the distribution of queries" - is optimal. We show that many aspects of this learning task are more difficult than the corresponding subtasks in the standard model.

Related

• An Improved Admissible Heuristic for Learning Optimal Bayesian Networks
• Learning the structure of Bayesian Networks: A quantitative assessment\n of the effect of different algorithmic schemes
• Learning Bayesian Networks: The Combination of Knowledge and Statistical Data
• Learning Bayesian Network Structure from Massive Datasets: The "Sparse Candidate" Algorithm
• Finding All Bayesian Network Structures within a Factor of Optimal