Paper: Convergence Results for Relational Bayesian Networks (at LICS 1998)

Authors: Manfred Jaeger

Abstract

Relational Bayesian networks are an extension of the method of probabilistic model construction by Bayesian networks. They define probability distributions on finite relational structures by conditioning the probability of a ground atom r(a₁, ..., a _n) on first-order properties of a₁, ..., a_n that have been established by previous random decisions. In this paper we investigate from a finite model theory perspective the convergence properties of the distributions defined in this manner. A subclass of relational Bayesian networks is identified that define distributions with convergence laws for first-order properties

BibTeX

  @InProceedings{Jaeger-ConvergenceResultsf,
    author = 	 {Manfred Jaeger},
    title = 	 {Convergence Results for Relational Bayesian Networks},
    booktitle =  {Proceedings of the Thirteenth Annual IEEE Symposium on Logic in Computer Science (LICS 1998)},
    year =	 {1998},
    month =	 {June}, 
    pages =      {44--55 },
    location =   {Indianapolis, IN, USA}, 
    publisher =	 {IEEE Computer Society Press}
  }