Complexity Analysis and Variational Inference for Interpretation-based Probabilistic Description Logic

Fabio Cozman, Rodrigo Polastro
Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, PMLR R7:117-125, 2009.

Abstract

This paper presents complexity analysis and variational methods for inference in probabilistic description logics featuring Boolean operators, quantification, qualified number restrictions, nominals, inverse roles and role hierarchies. Inference is shown to be PEXP-complete, and variational methods are designed so as to exploit logical inference whenever possible.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR7-cozman09a, title = {Complexity Analysis and Variational Inference for Interpretation-based Probabilistic Description Logic}, author = {Cozman, Fabio and Polastro, Rodrigo}, booktitle = {Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence}, pages = {117--125}, year = {2009}, editor = {Bilmes, Jeff and Ng, Andrew Y.}, volume = {R7}, series = {Proceedings of Machine Learning Research}, month = {18--21 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r7/main/assets/cozman09a/cozman09a.pdf}, url = {https://proceedings.mlr.press/r7/cozman09a.html}, abstract = {This paper presents complexity analysis and variational methods for inference in probabilistic description logics featuring Boolean operators, quantification, qualified number restrictions, nominals, inverse roles and role hierarchies. Inference is shown to be PEXP-complete, and variational methods are designed so as to exploit logical inference whenever possible.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Complexity Analysis and Variational Inference for Interpretation-based Probabilistic Description Logic %A Fabio Cozman %A Rodrigo Polastro %B Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2009 %E Jeff Bilmes %E Andrew Y. Ng %F pmlr-vR7-cozman09a %I PMLR %P 117--125 %U https://proceedings.mlr.press/r7/cozman09a.html %V R7 %X This paper presents complexity analysis and variational methods for inference in probabilistic description logics featuring Boolean operators, quantification, qualified number restrictions, nominals, inverse roles and role hierarchies. Inference is shown to be PEXP-complete, and variational methods are designed so as to exploit logical inference whenever possible. %Z Reissued by PMLR on 04 October 2026.
APA
Cozman, F. & Polastro, R.. (2009). Complexity Analysis and Variational Inference for Interpretation-based Probabilistic Description Logic. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R7:117-125 Available from https://proceedings.mlr.press/r7/cozman09a.html. Reissued by PMLR on 04 October 2026.

Related Material