Probabilistic graphical models specified by probabilistic logic programs: Semantics and complexity

Fabio Gagliardi Cozman, Denis Deratani Mau

Resultado de la investigación: Contribución a una revistaArtículo de la conferenciarevisión exhaustiva

5 Citas (Scopus)

Resumen

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.

Idioma originalInglés
Páginas (desde-hasta)110-122
Número de páginas13
PublicaciónJournal of Machine Learning Research
Volumen52
N.º2016
EstadoPublicada - 2016
Publicado de forma externa
Evento8th International Conference on Probabilistic Graphical Models, PGM 2016 - Lugano, Suiza
Duración: 6 sep 20169 sep 2016

Huella

Profundice en los temas de investigación de 'Probabilistic graphical models specified by probabilistic logic programs: Semantics and complexity'. En conjunto forman una huella única.

Citar esto