Probabilistic Conditional Preference Networks (UAI 2013)

Damien Bigot (1) , Hélène Fargier (1, 2) , Jérôme Mengin (1) , Bruno Zanuttini (3)

1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage
2 CNRS - Centre National de la Recherche Scientifique
3 Equipe MAD - Laboratoire GREYC - UMR6072

This paper proposes a \probabilistic" extension of conditional preference networks as a way to compactly represent a probability distributions over preference orderings. It studies the probabilistic counterparts of the main reasoning tasks, namely dominance testing and optimisation from the algorithmical and complexity viewpoints. Efficient algorithms for tree-structured probabilistic CP-nets are given. As a by-product we obtain a lineartime algorithm for dominance testing in standard, tree-structured CP-nets.

Domaines: Intelligence artificielle [cs.AI]; Modélisation et simulation; Logique en informatique [cs.LO]; Apprentissage [cs.LG]

Damien Bigot, Hélène Fargier, Jérôme Mengin, Bruno Zanuttini. Probabilistic Conditional Preference Networks (UAI 2013). 29th Conference on Uncertainty in Artificial Intelligence (UAI 2013), Jul 2013, Bellevue, Washington, United States. ⟨hal-00944185⟩