A Linear Programming Approach for Learning Bounded Treewidth Bayesian Networks
2013 (English)Manuscript (preprint) (Other academic)
In many applications, one wants to compute conditional probabilities from a Bayesian network. This inference problem is NP-hard in general but becomes tractable when the network has bounded treewidth. Motivated by the needs of applications, we study learning bounded treewidth Bayesian networks. We formulate this problem as a mixed integer linear program (MILP) which can be solved by an anytime algorithm.
Place, publisher, year, edition, pages
Tree-width, linear programming, Bayesian networks
Probability Theory and Statistics
IdentifiersURN: urn:nbn:se:kth:diva-121702OAI: oai:DiVA.org:kth-121702DiVA: diva2:619426
QS 20132013-05-032013-05-032016-02-02Bibliographically approved