Improved Local Search in Bayesian Networks Structure Learning

Mauro Scanagatta, Giorgio Corani, Marco Zaffalon
Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks, PMLR 73:45-56, 2017.

Abstract

We present a novel approach for score-based structure learning of Bayesian network, which couples an existing ordering-based algorithm for structure optimization with a novel operator for exploring the neighborhood of a given order in the space of the orderings. Our approach achieves state-of-the-art performances in data sets containing thousands of variables.

Cite this Paper

BibTeX
@InProceedings{pmlr-v73-scanagatta17a, title = {Improved Local Search in Bayesian Networks Structure Learning}, author = {Scanagatta, Mauro and Corani, Giorgio and Zaffalon, Marco}, booktitle = {Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks}, pages = {45--56}, year = {2017}, editor = {Hyttinen, Antti and Suzuki, Joe and Malone, Brandon}, volume = {73}, series = {Proceedings of Machine Learning Research}, month = {20--22 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v73/scanagatta17a/scanagatta17a.pdf}, url = {https://proceedings.mlr.press/v73/scanagatta17a.html}, abstract = {We present a novel approach for score-based structure learning of Bayesian network, which couples an existing ordering-based algorithm for structure optimization with a novel operator for exploring the neighborhood of a given order in the space of the orderings. Our approach achieves state-of-the-art performances in data sets containing thousands of variables. } }
Endnote
%0 Conference Paper %T Improved Local Search in Bayesian Networks Structure Learning %A Mauro Scanagatta %A Giorgio Corani %A Marco Zaffalon %B Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks %C Proceedings of Machine Learning Research %D 2017 %E Antti Hyttinen %E Joe Suzuki %E Brandon Malone %F pmlr-v73-scanagatta17a %I PMLR %P 45--56 %U https://proceedings.mlr.press/v73/scanagatta17a.html %V 73 %X We present a novel approach for score-based structure learning of Bayesian network, which couples an existing ordering-based algorithm for structure optimization with a novel operator for exploring the neighborhood of a given order in the space of the orderings. Our approach achieves state-of-the-art performances in data sets containing thousands of variables.
APA
Scanagatta, M., Corani, G. & Zaffalon, M.. (2017). Improved Local Search in Bayesian Networks Structure Learning. Proceedings of The 3rd International Workshop on Advanced Methodologies for Bayesian Networks, in Proceedings of Machine Learning Research 73:45-56 Available from https://proceedings.mlr.press/v73/scanagatta17a.html.

Related Material