Bayesian Model Averaging Using the k-best Bayesian Network Structures

Jin Tian, Ru He, Lavanya Ram
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:596-604, 2010.

Abstract

We study the problem of learning Bayesian net- work structures from data. We develop an al- gorithm for finding the k-best Bayesian net- work structures. We propose to compute the posterior probabilities of hypotheses of interest by Bayesian model averaging over the k-best Bayesian networks. We present empirical results on structural discovery over several real and syn- thetic data sets and show that the method outper- forms the model selection method and the state- of-the-art MCMC methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-tian10a, title = {{B}ayesian Model Averaging Using the k-best {B}ayesian Network Structures}, author = {Tian, Jin and He, Ru and Ram, Lavanya}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {596--604}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/tian10a/tian10a.pdf}, url = {https://proceedings.mlr.press/r8/tian10a.html}, abstract = {We study the problem of learning Bayesian net- work structures from data. We develop an al- gorithm for finding the k-best Bayesian net- work structures. We propose to compute the posterior probabilities of hypotheses of interest by Bayesian model averaging over the k-best Bayesian networks. We present empirical results on structural discovery over several real and syn- thetic data sets and show that the method outper- forms the model selection method and the state- of-the-art MCMC methods.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Bayesian Model Averaging Using the k-best Bayesian Network Structures %A Jin Tian %A Ru He %A Lavanya Ram %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-tian10a %I PMLR %P 596--604 %U https://proceedings.mlr.press/r8/tian10a.html %V R8 %X We study the problem of learning Bayesian net- work structures from data. We develop an al- gorithm for finding the k-best Bayesian net- work structures. We propose to compute the posterior probabilities of hypotheses of interest by Bayesian model averaging over the k-best Bayesian networks. We present empirical results on structural discovery over several real and syn- thetic data sets and show that the method outper- forms the model selection method and the state- of-the-art MCMC methods. %Z Reissued by PMLR on 04 October 2026.
APA
Tian, J., He, R. & Ram, L.. (2010). Bayesian Model Averaging Using the k-best Bayesian Network Structures. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:596-604 Available from https://proceedings.mlr.press/r8/tian10a.html. Reissued by PMLR on 04 October 2026.

Related Material