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 #P, #NP, and even #EXP. 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.
|Number of pages||13|
|Journal||Journal of Machine Learning Research|
|State||Published - 2016|
|Event||8th International Conference on Probabilistic Graphical Models, PGM 2016 - Lugano, Switzerland|
Duration: 6 Sep 2016 → 9 Sep 2016
- Complexity theory
- Probabilistic logic programming