Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories

Rodrigo de Salvo Braz, Ciaran O’Reilly
Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, PMLR R15:341-350, 2017.

Abstract

Probabilistic Inference Modulo Theories (PIMT) is a recent framework that expands exact infer- ence on graphical models to use richer languages that include arithmetic, equalities, and inequali- ties on both integers and real numbers. In this pa- per, we expand PIMT to a lifted version that also processes random functions and relations. This enhancement is achieved by adapting Inversion, a method from Lifted First-Order Probabilistic Inference literature, to also be modulo theories. This results in the first algorithm for exact proba- bilistic inference that efficiently and simultane- ously exploits random relations and functions, arithmetic, equalities and inequalities.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR15-braz17a, title = {Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories}, author = {Braz, Rodrigo de Salvo and O'Reilly, Ciaran}, booktitle = {Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence}, pages = {341--350}, year = {2017}, editor = {Elidan, Gal and Kersting, Kristian}, volume = {R15}, series = {Proceedings of Machine Learning Research}, month = {11--15 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r15/main/assets/braz17a/braz17a.pdf}, url = {https://proceedings.mlr.press/r15/braz17a.html}, abstract = {Probabilistic Inference Modulo Theories (PIMT) is a recent framework that expands exact infer- ence on graphical models to use richer languages that include arithmetic, equalities, and inequali- ties on both integers and real numbers. In this pa- per, we expand PIMT to a lifted version that also processes random functions and relations. This enhancement is achieved by adapting Inversion, a method from Lifted First-Order Probabilistic Inference literature, to also be modulo theories. This results in the first algorithm for exact proba- bilistic inference that efficiently and simultane- ously exploits random relations and functions, arithmetic, equalities and inequalities.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories %A Rodrigo de Salvo Braz %A Ciaran O’Reilly %B Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2017 %E Gal Elidan %E Kristian Kersting %F pmlr-vR15-braz17a %I PMLR %P 341--350 %U https://proceedings.mlr.press/r15/braz17a.html %V R15 %X Probabilistic Inference Modulo Theories (PIMT) is a recent framework that expands exact infer- ence on graphical models to use richer languages that include arithmetic, equalities, and inequali- ties on both integers and real numbers. In this pa- per, we expand PIMT to a lifted version that also processes random functions and relations. This enhancement is achieved by adapting Inversion, a method from Lifted First-Order Probabilistic Inference literature, to also be modulo theories. This results in the first algorithm for exact proba- bilistic inference that efficiently and simultane- ously exploits random relations and functions, arithmetic, equalities and inequalities. %Z Reissued by PMLR on 04 October 2026.
APA
Braz, R.d.S. & O’Reilly, C.. (2017). Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories. Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R15:341-350 Available from https://proceedings.mlr.press/r15/braz17a.html. Reissued by PMLR on 04 October 2026.

Related Material