Bayesian network learning with cutting planes

James Cussens
Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, PMLR R9:181-188, 2011.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR9-cussens11a, title = {{B}ayesian network learning with cutting planes}, author = {Cussens, James}, booktitle = {Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence}, pages = {181--188}, year = {2011}, editor = {Cozman, Fabio and Pfeffer, Avi}, volume = {R9}, series = {Proceedings of Machine Learning Research}, month = {14--17 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r9/main/assets/cussens11a/cussens11a.pdf}, url = {https://proceedings.mlr.press/r9/cussens11a.html}, 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.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Bayesian network learning with cutting planes %A James Cussens %B Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2011 %E Fabio Cozman %E Avi Pfeffer %F pmlr-vR9-cussens11a %I PMLR %P 181--188 %U https://proceedings.mlr.press/r9/cussens11a.html %V R9 %X 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. %Z Reissued by PMLR on 04 October 2026.
APA
Cussens, J.. (2011). Bayesian network learning with cutting planes. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R9:181-188 Available from https://proceedings.mlr.press/r9/cussens11a.html. Reissued by PMLR on 04 October 2026.

Related Material