Bayesian network learning with cutting planes

Abstract

The problem of learning the structure of Bayesian networks from complete discrete data with a limit on parent set size is considered. Learning is cast explicitly as an optimisation problem where the goal is to find a BN structure which maximises log marginal likelihood (BDe score). Integer programming, specifically the SCIP framework, is used to solve this optimisation problem. Acyclicity constraints are added to the integer program (IP) during solving in the form of cutting planes. Finding good cutting planes is the key to the success of the approach -the search for such cutting planes is effected using a sub-IP. Results show that this is a particularly fast method for exact BN learning.

References in corpus (3)

• A simple approach for finding the globally optimal Bayesian network structure
• On Sensitivity of the MAP Bayesian Network Structure to the Equivalent Sample Size Parameter
• Bayesian network learning by compiling to weighted MAX-SAT

Cited by in corpus (7)

• Searching Multiregression Dynamic Models of Resting-State fMRI Networks Using Integer Programming
• An Improved Admissible Heuristic for Learning Optimal Bayesian Networks
• Advances in Learning Bayesian Networks of Bounded Treewidth
• Estimating causal structure using conditional DAG models
• Structure Learning in Bayesian Networks of Moderate Size by Efficient Sampling
• Exact Maximum Margin Structure Learning of Bayesian Networks
• Incorporating Type II Error Probabilities from Independence Tests into Score-Based Learning of Bayesian Network Structure