On the Conditional Independence Implication Problem: A Lattice-Theoretic Approach

Simple item page
dc.creatorNiepert, Mathias
dc.creatorVan Gucht, Dirk
dc.creatorGyssens, Marc
dc.date2008-10-31
dc.date.accessioned2026-07-07T10:14:36Z
dc.date.available2026-07-07T10:14:36Z
dc.descriptionA lattice-theoretic framework is introduced that permits the study of the conditional independence (CI) implication problem relative to the class of discrete probability measures. Semi-lattices are associated with CI statements and a finite, sound and complete inference system relative to semi-lattice inclusions is presented. This system is shown to be (1) sound and complete for saturated CI statements, (2) complete for general CI statements, and (3) sound and complete for stable CI statements. These results yield a criterion that can be used to falsify instances of the implication problem and several heuristics are derived that approximate this "lattice-exclusion" criterion in polynomial time. Finally, we provide experimental results that relate our work to results obtained from other existing inference algorithms.
dc.identifierhttps://arxiv.org/abs/0810.5717
dc.identifierhttp://arxiv.org/abs/0810.5717
dc.identifierProceedings of the 24th Conference on Uncertainty in Artificial Intelligence, 2008, pages 435-443
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/172936
dc.subjectArtificial Intelligence
dc.subjectDiscrete Mathematics
dc.titleOn the Conditional Independence Implication Problem: A Lattice-Theoretic Approach
dc.typetext

Files

Collections

arXiv