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

DOI10.1016/j.ijar.2019.04.003zbMath1460.68042OpenAlexW2937945793WikidataQ128019482 ScholiaQ128019482MaRDI QIDQ2283277

Fabio Gagliardi Cozman, Denis Deratani Mauá

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

zbMATH Keywords

Bayesian networksfinite model theorydescriptive complexityprobabilistic logicprobabilistic relational modelszero/one laws

Mathematics Subject Classification ID

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

Related Items (4)

An Asymptotic Analysis of Probabilistic Logic Programming, with Implications for Expressing Projective Families of Distributions ⋮ Asymptotic elimination of partially continuous aggregation functions in directed graphical models ⋮ The joy of probabilistic answer set programming: semantics, complexity, expressivity, inference ⋮ Some thoughts on knowledge-enhanced machine learning

Uses Software

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Negative probabilities in probabilistic logic programs
• Finite model theory and its applications.
• Elements of finite model theory.
• The complexity of combinatorial problems with succinct input representation
• The polynomial-time hierarchy
• Probabilistic Horn abduction and Bayesian networks
• Decidability and expressiveness for first-order logics of probability
• PR-OWL - a language for defining probabilistic ontologies
• The complexity of Bayesian networks specified by propositional and relational languages
• Descriptive complexity of \(\#\)P functions
• Complex probabilistic modeling with recursive relational Bayesian networks
• The descriptive complexity of Bayesian network specifications
• Markov properties for mixed graphs
• Probabilistic inductive logic programming. Theory and applications
• Soft computing in ontologies and semantic web.
• Concerning measures in first order calculi
• Probabilistic Databases
• Complexity of the first-order theory of almost all finite structures
• Reachability is harder for directed than for undirected finite graphs
• Logical and Relational Learning
• Modeling and Reasoning with Bayesian Networks
• Marginals of DAG-Isomorphic Independence Models
• The DL-Lite Family and Relations
• Probabilities over rich languages, testing and randomness
• Probabilities on finite models
• Complexity classes defined by counting quantifiers
• Lower complexity bounds for lifted inference
• Inference and learning in probabilistic logic programs using weighted Boolean formulas
• 10.1162/jmlr.2003.3.4-5.993
• On the Semantics and Complexity of Probabilistic Logic Programs
• Model-Theoretic Expressivity Analysis
• Random Graphs
• Networks

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