Lower complexity bounds for lifted inference

DOI10.1017/S1471068413000707zbMATH Open1379.68298arXiv1204.3255MaRDI QIDQ4592980FDOQ4592980

Manfred Jaeger

Publication date: 9 November 2017

Published in: Theory and Practice of Logic Programming (Search for Journal in Brave)

Abstract: One of the big challenges in the development of probabilistic relational (or probabilistic logical) modeling and learning frameworks is the design of inference techniques that operate on the level of the abstract model representation language, rather than on the level of ground, propositional instances of the model. Numerous approaches for such "lifted inference" techniques have been proposed. While it has been demonstrated that these techniques will lead to significantly more efficient inference on some specific models, there are only very recent and still quite restricted results that show the feasibility of lifted inference on certain syntactically defined classes of models. Lower complexity bounds that imply some limitations for the feasibility of lifted inference on more expressive model classes were established early on in (Jaeger 2000). However, it is not immediate that these results also apply to the type of modeling languages that currently receive the most attention, i.e., weighted, quantifier-free formulas. In this paper we extend these earlier results, and show that under the assumption that NETIME =/= ETIME, there is no polynomial lifted inference algorithm for knowledge bases of weighted, quantifier- and function-free formulas. Further strengthening earlier results, this is also shown to hold for approximate inference, and for knowledge bases not containing the equality predicate.

Full work available at URL: https://arxiv.org/abs/1204.3255

Recommendations

• On the complexity of inference about probabilistic relational models
• The complexity of Bayesian networks specified by propositional and relational languages
• Lifted variable elimination: decoupling the operators from the constraint language
• A survey of lifted inference approaches for probabilistic logic programming under the distribution semantics
• Inference in probabilistic logic programs using lifted explanations

zbMATH Keywords

lifted inferenceprobabilistic-logic models

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17) Logic in artificial intelligence (68T27)

Cites Work

• Probabilities on finite models
• Title not available (Why is that?)
• Markov logic networks
• Probabilistic Horn abduction and Bayesian networks
• Title not available (Why is that?)
• Representing Causal Information About a Probabilistic Process
• On the complexity of inference about probabilistic relational models
• Title not available (Why is that?)

Cited In (5)

• Lifted algorithms for symmetric weighted first-order model sampling
• Weighted First-Order Model Counting in the Two-Variable Fragment With Counting Quantifiers
• Languages for probabilistic modeling over structured and relational domains
• The complexity of Bayesian networks specified by propositional and relational languages
• The finite model theory of Bayesian network specifications: descriptive complexity and zero/one laws

Uses Software

• BLOG

This page was built for publication: Lower complexity bounds for lifted inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4592980)