The complexity of MAP inference in Bayesian networks specified through logical languages

Denis D. Mauá, Cassio P. De Campos, Fabio G. Cozman

Research output: Contribution to conferenceConference Paper

6 Scopus citations

Abstract

We study the computational complexity of finding maximum a posteriori configurations in Bayesian networks whose probabilities are specified by logical formulas. This approach leads to a fine grained study in which local information such as contextsensitive independence and determinism can be considered. It also allows us to characterize more precisely the jump from tractability to NP-hardness and beyond, and to consider the complexity introduced by evidence alone.
Original languageAmerican English
Pages889-895
Number of pages7
StatePublished - 1 Jan 2015
Externally publishedYes
EventIJCAI International Joint Conference on Artificial Intelligence -
Duration: 1 Jan 2015 → …

Conference

ConferenceIJCAI International Joint Conference on Artificial Intelligence
Period1/01/15 → …

Fingerprint

Dive into the research topics of 'The complexity of MAP inference in Bayesian networks specified through logical languages'. Together they form a unique fingerprint.

Cite this