Learning Optimal Chain Graphs with Answer Set Programming

Dag Sonntag Linköping University, Matti Järvisalo, Jose Pena Linkoping University, Antti Hyttinen
Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, PMLR R13:566-575, 2015.

Abstract

Learning an optimal chain graph for a given probability distribution is an important but at the same time very hard computational problem. We present a new approach to solve this problem for various objective functions, and without making any assumption on the probability distribution at hand. Our approach is based on encoding the learning problem declaratively using the answer set programming (ASP) paradigm. Empirical results show that our approach provides at least as accurate solutions as the best solutions provided by the existing algorithms, and overall provides better accuracy than any single previous algorithm.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR13-university15l, title = {Learning Optimal Chain Graphs with Answer Set Programming}, author = {University, Dag Sonntag Link{\"o}ping and J{\"a}rvisalo, Matti and University, Jose Pena Linkoping and Hyttinen, Antti}, booktitle = {Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence}, pages = {566--575}, year = {2015}, editor = {Meila, Marina and Heskes, Tom}, volume = {R13}, series = {Proceedings of Machine Learning Research}, month = {12--16 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r13/main/assets/university15l/university15l.pdf}, url = {https://proceedings.mlr.press/r13/university15l.html}, abstract = {Learning an optimal chain graph for a given probability distribution is an important but at the same time very hard computational problem. We present a new approach to solve this problem for various objective functions, and without making any assumption on the probability distribution at hand. Our approach is based on encoding the learning problem declaratively using the answer set programming (ASP) paradigm. Empirical results show that our approach provides at least as accurate solutions as the best solutions provided by the existing algorithms, and overall provides better accuracy than any single previous algorithm.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Learning Optimal Chain Graphs with Answer Set Programming %A Dag Sonntag Linköping University %A Matti Järvisalo %A Jose Pena Linkoping University %A Antti Hyttinen %B Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2015 %E Marina Meila %E Tom Heskes %F pmlr-vR13-university15l %I PMLR %P 566--575 %U https://proceedings.mlr.press/r13/university15l.html %V R13 %X Learning an optimal chain graph for a given probability distribution is an important but at the same time very hard computational problem. We present a new approach to solve this problem for various objective functions, and without making any assumption on the probability distribution at hand. Our approach is based on encoding the learning problem declaratively using the answer set programming (ASP) paradigm. Empirical results show that our approach provides at least as accurate solutions as the best solutions provided by the existing algorithms, and overall provides better accuracy than any single previous algorithm. %Z Reissued by PMLR on 04 October 2026.
APA
University, D.S.L., Järvisalo, M., University, J.P.L. & Hyttinen, A.. (2015). Learning Optimal Chain Graphs with Answer Set Programming. Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R13:566-575 Available from https://proceedings.mlr.press/r13/university15l.html. Reissued by PMLR on 04 October 2026.

Related Material