The finite model theory of Bayesian network specifications: descriptive complexity and zero/one laws

DOI10.1016/J.IJAR.2019.04.003zbMATH Open1460.68042OpenAlexW2937945793WikidataQ128019482 ScholiaQ128019482MaRDI QIDQ2283277FDOQ2283277

Authors: Fabio Gagliardi Cozman, D. D. Maua 

Publication date: 30 December 2019

Published in: International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ijar.2019.04.003

Recommendations

• The descriptive complexity of Bayesian network specifications
• The complexity of Bayesian networks specified by propositional and relational languages
• On the complexity of propositional and relational credal networks
• Computational complexity and the expressive power of logics
• Conditional probability logic, lifted Bayesian networks, and almost sure quantifier elimination

zbMATH Keywords

Bayesian networksfinite model theorydescriptive complexityprobabilistic logicprobabilistic relational modelszero/one laws

Mathematics Subject Classification ID

Probabilistic graphical models (62H22) Probability and inductive logic (03B48) Model theory of finite structures (03C13) Specification and verification (program logics, model checking, etc.) (68Q60) Logic in artificial intelligence (68T27) Descriptive complexity and finite models (68Q19)

Cites Work

• PR-OWL - a language for defining probabilistic ontologies
• Title not available (Why is that?)
• Random Graphs
• Probabilistic graphical models.
• 10.1162/jmlr.2003.3.4-5.993
• Title not available (Why is that?)
• Title not available (Why is that?)
• Modeling and Reasoning with Bayesian Networks
• Networks. An introduction.
• The DL-Lite Family and Relations
• Probabilities on finite models
• Title not available (Why is that?)
• Concerning measures in first order calculi
• Complexity classes defined by counting quantifiers
• Title not available (Why is that?)
• Elements of finite model theory.
• Title not available (Why is that?)
• Probabilistic inductive logic programming. Theory and applications
• Title not available (Why is that?)
• Title not available (Why is that?)
• The polynomial-time hierarchy
• Reachability is harder for directed than for undirected finite graphs
• Title not available (Why is that?)
• The complexity of combinatorial problems with succinct input representation
• Finite model theory and its applications.
• Probabilistic Horn abduction and Bayesian networks
• Markov properties for mixed graphs
• Probabilities over rich languages, testing and randomness
• Probabilistic databases
• Inference and learning in probabilistic logic programs using weighted Boolean formulas
• Title not available (Why is that?)
• Logical and Relational Learning
• Decidability and expressiveness for first-order logics of probability
• Negative probabilities in probabilistic logic programs
• Title not available (Why is that?)
• Complexity of the first-order theory of almost all finite structures
• Probabilistic programming languages: independent choices and deterministic systems
• Model-Theoretic Expressivity Analysis
• Descriptive complexity of \(\#\)P functions
• Soft computing in ontologies and semantic web.
• The complexity of Bayesian networks specified by propositional and relational languages
• Complex probabilistic modeling with recursive relational Bayesian networks
• Lower complexity bounds for lifted inference
• On the semantics and complexity of probabilistic logic programs
• Marginals of DAG-Isomorphic Independence Models
• The descriptive complexity of Bayesian network specifications

Cited In (8)

• The generalised distribution semantics and projective families of distributions
• Asymptotic elimination of partially continuous aggregation functions in directed graphical models
• An Asymptotic Analysis of Probabilistic Logic Programming, with Implications for Expressing Projective Families of Distributions
• The descriptive complexity of Bayesian network specifications
• Some thoughts on knowledge-enhanced machine learning
• Relating description complexity to entropy
• The joy of probabilistic answer set programming: semantics, complexity, expressivity, inference
• The complexity of Bayesian networks specified by propositional and relational languages

Uses Software

• BUGS
• IBAL
• Church
• Stan
• KnowRob
• PR-OWL
• BLOG
• BayesOWL

This page was built for publication: The finite model theory of Bayesian network specifications: descriptive complexity and zero/one laws

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2283277)