An Asymptotic Analysis of Probabilistic Logic Programming, with Implications for Expressing Projective Families of Distributions. Issue 6 (November 2021)

• Record Type: Journal Article
• Authors: WEITKÄMPER, FELIX Q.
• Is Part Of: Theory and practice of logic programming. Volume 21:Issue 6(2021)
• Page Start: 802
• Page End: 817
• Publication Date: 2021-11
• Subjects: probabilistic logic programming -- asymptotic quantifier elimination -- determinate logic programs -- projective families of distributions -- finite model theory -- distribution semantics; Logic programming -- Periodicals; Artificial intelligence -- Computer programs -- Periodicals; Constraint programming (Computer science) -- Periodicals; 005.115
• DOI: 10.1017/S1471068421000314
• Languages: English
• ISSNs: 1471-0684

Abstract

Abstract: Probabilistic logic programming is a major part of statistical relational artificial intelligence, where approaches from logic and probability are brought together to reason about and learn from relational domains in a setting of uncertainty. However, the behaviour of statistical relational representations across variable domain sizes is complex, and scaling inference and learning to large domains remains a significant challenge. In recent years, connections have emerged between domain size dependence, lifted inference and learning from sampled subpopulations. The asymptotic behaviour of statistical relational representations has come under scrutiny, and projectivity was investigated as the strongest form of domain size dependence, in which query marginals are completely independent of the domain size. In this contribution we show that every probabilistic logic program under the distribution semantics is asymptotically equivalent to an acyclic probabilistic logic program consisting only of determinate clauses over probabilistic facts. We conclude that every probabilistic logic program inducing a projective family of distributions is in fact everywhere equivalent to a program from this fragment, and we investigate the consequences for the projective families of distributions expressible by probabilistic logic programs.