Learning Bayesian Networks with Cops and Robbers

Topi Talvitie, Pekka Parviainen
Proceedings of the 10th International Conference on Probabilistic Graphical Models, PMLR 138:473-484, 2020.

Abstract

Constraint-based methods for learning structures of Bayesian networks are based on testing conditional independencies between variables and constructing a structure that expresses the same conditional independencies as indicated by the tests. We present a constraint-based algorithm that learns the structure of a Bayesian network by simulating a cops-and-a-robber game. The algorithm is designed for learning structures of low treewidth distributions and in such case it conducts conditional independence tests only with small conditioning sets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v138-talvitie20a, title = {Learning Bayesian Networks with Cops and Robbers}, author = {Talvitie, Topi and Parviainen, Pekka}, booktitle = {Proceedings of the 10th International Conference on Probabilistic Graphical Models}, pages = {473--484}, year = {2020}, editor = {Jaeger, Manfred and Nielsen, Thomas Dyhre}, volume = {138}, series = {Proceedings of Machine Learning Research}, month = {23--25 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v138/talvitie20a/talvitie20a.pdf}, url = {https://proceedings.mlr.press/v138/talvitie20a.html}, abstract = {Constraint-based methods for learning structures of Bayesian networks are based on testing conditional independencies between variables and constructing a structure that expresses the same conditional independencies as indicated by the tests. We present a constraint-based algorithm that learns the structure of a Bayesian network by simulating a cops-and-a-robber game. The algorithm is designed for learning structures of low treewidth distributions and in such case it conducts conditional independence tests only with small conditioning sets. } }
Endnote
%0 Conference Paper %T Learning Bayesian Networks with Cops and Robbers %A Topi Talvitie %A Pekka Parviainen %B Proceedings of the 10th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2020 %E Manfred Jaeger %E Thomas Dyhre Nielsen %F pmlr-v138-talvitie20a %I PMLR %P 473--484 %U https://proceedings.mlr.press/v138/talvitie20a.html %V 138 %X Constraint-based methods for learning structures of Bayesian networks are based on testing conditional independencies between variables and constructing a structure that expresses the same conditional independencies as indicated by the tests. We present a constraint-based algorithm that learns the structure of a Bayesian network by simulating a cops-and-a-robber game. The algorithm is designed for learning structures of low treewidth distributions and in such case it conducts conditional independence tests only with small conditioning sets.
APA
Talvitie, T. & Parviainen, P.. (2020). Learning Bayesian Networks with Cops and Robbers. Proceedings of the 10th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 138:473-484 Available from https://proceedings.mlr.press/v138/talvitie20a.html.

Related Material