Probabilistic Graphical Models Specified by Probabilistic Logic Programs: Semantics and Complexity

Fabio Gagliardi Cozman, Denis Deratani Mauá
Proceedings of the Eighth International Conference on Probabilistic Graphical Models, PMLR 52:110-122, 2016.

Abstract

We look at probabilistic logic programs as a specification language for probabilistic models, and study their interpretation and complexity. Acyclic programs specify Bayesian networks, and, depending on constraints on logical atoms, their inferential complexity reaches complexity classes #\mathsfP, #\mathsfNP, and even #\mathsfEXP. We also investigate (cyclic) stratified probabilistic logic programs, showing that they have the same complexity as acyclic probabilistic logic programs, and that they can be depicted using chain graphs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v52-cozman16, title = {Probabilistic Graphical Models Specified by Probabilistic Logic Programs: Semantics and Complexity}, author = {Cozman, Fabio Gagliardi and Mauá, Denis Deratani}, booktitle = {Proceedings of the Eighth International Conference on Probabilistic Graphical Models}, pages = {110--122}, year = {2016}, editor = {Antonucci, Alessandro and Corani, Giorgio and Campos}, Cassio Polpo}, volume = {52}, series = {Proceedings of Machine Learning Research}, address = {Lugano, Switzerland}, month = {06--09 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v52/cozman16.pdf}, url = {https://proceedings.mlr.press/v52/cozman16.html}, abstract = {We look at probabilistic logic programs as a specification language for probabilistic models, and study their interpretation and complexity. Acyclic programs specify Bayesian networks, and, depending on constraints on logical atoms, their inferential complexity reaches complexity classes #\mathsfP, #\mathsfNP, and even #\mathsfEXP. We also investigate (cyclic) stratified probabilistic logic programs, showing that they have the same complexity as acyclic probabilistic logic programs, and that they can be depicted using chain graphs.} }
Endnote
%0 Conference Paper %T Probabilistic Graphical Models Specified by Probabilistic Logic Programs: Semantics and Complexity %A Fabio Gagliardi Cozman %A Denis Deratani Mauá %B Proceedings of the Eighth International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2016 %E Alessandro Antonucci %E Giorgio Corani %E Cassio Polpo Campos} %F pmlr-v52-cozman16 %I PMLR %P 110--122 %U https://proceedings.mlr.press/v52/cozman16.html %V 52 %X We look at probabilistic logic programs as a specification language for probabilistic models, and study their interpretation and complexity. Acyclic programs specify Bayesian networks, and, depending on constraints on logical atoms, their inferential complexity reaches complexity classes #\mathsfP, #\mathsfNP, and even #\mathsfEXP. We also investigate (cyclic) stratified probabilistic logic programs, showing that they have the same complexity as acyclic probabilistic logic programs, and that they can be depicted using chain graphs.
RIS
TY - CPAPER TI - Probabilistic Graphical Models Specified by Probabilistic Logic Programs: Semantics and Complexity AU - Fabio Gagliardi Cozman AU - Denis Deratani Mauá BT - Proceedings of the Eighth International Conference on Probabilistic Graphical Models DA - 2016/08/15 ED - Alessandro Antonucci ED - Giorgio Corani ED - Cassio Polpo Campos} ID - pmlr-v52-cozman16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 52 SP - 110 EP - 122 L1 - http://proceedings.mlr.press/v52/cozman16.pdf UR - https://proceedings.mlr.press/v52/cozman16.html AB - We look at probabilistic logic programs as a specification language for probabilistic models, and study their interpretation and complexity. Acyclic programs specify Bayesian networks, and, depending on constraints on logical atoms, their inferential complexity reaches complexity classes #\mathsfP, #\mathsfNP, and even #\mathsfEXP. We also investigate (cyclic) stratified probabilistic logic programs, showing that they have the same complexity as acyclic probabilistic logic programs, and that they can be depicted using chain graphs. ER -
APA
Cozman, F.G. & Mauá, D.D.. (2016). Probabilistic Graphical Models Specified by Probabilistic Logic Programs: Semantics and Complexity. Proceedings of the Eighth International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 52:110-122 Available from https://proceedings.mlr.press/v52/cozman16.html.

Related Material