EDML: A Method for Learning Parameters in Bayesian Networks

Arthur Choi, Khaled S. Refaat, Adnan Darwiche
Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, PMLR R9:143-152, 2011.

Abstract

We propose a method called EDML for learning MAP parameters in binary Bayesian networks under incomplete data. The method assumes Beta priors and can be used to learn maximum likelihood parameters when the priors are uninformative. EDML exhibits interesting behaviors, especially when compared to EM. We introduce EDML, explain its origin, and study some of its properties both analytically and empirically.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR9-choi11a, title = {{EDML}: A Method for Learning Parameters in {B}ayesian Networks}, author = {Choi, Arthur and Refaat, Khaled S. and Darwiche, Adnan}, booktitle = {Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence}, pages = {143--152}, 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/choi11a/choi11a.pdf}, url = {https://proceedings.mlr.press/r9/choi11a.html}, abstract = {We propose a method called EDML for learning MAP parameters in binary Bayesian networks under incomplete data. The method assumes Beta priors and can be used to learn maximum likelihood parameters when the priors are uninformative. EDML exhibits interesting behaviors, especially when compared to EM. We introduce EDML, explain its origin, and study some of its properties both analytically and empirically.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T EDML: A Method for Learning Parameters in Bayesian Networks %A Arthur Choi %A Khaled S. Refaat %A Adnan Darwiche %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-choi11a %I PMLR %P 143--152 %U https://proceedings.mlr.press/r9/choi11a.html %V R9 %X We propose a method called EDML for learning MAP parameters in binary Bayesian networks under incomplete data. The method assumes Beta priors and can be used to learn maximum likelihood parameters when the priors are uninformative. EDML exhibits interesting behaviors, especially when compared to EM. We introduce EDML, explain its origin, and study some of its properties both analytically and empirically. %Z Reissued by PMLR on 04 October 2026.
APA
Choi, A., Refaat, K.S. & Darwiche, A.. (2011). EDML: A Method for Learning Parameters in Bayesian Networks. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R9:143-152 Available from https://proceedings.mlr.press/r9/choi11a.html. Reissued by PMLR on 04 October 2026.

Related Material