Exploiting case-based independence for approximating marginal probabilities

Solomon Eyal Shimony, Eugene Santos

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

Computing marginal probabilities in Bayes networks is a hard problem. Deterministic anytime approximation schemes accumulate the probability mass in a small number of value assignments to the network variables. Under certain assumptions, the probability mass in the assignments is sufficient to obtain a good approximation. Such methods are especially useful for highly connected networks, where the topology makes the exact algorithms intractable. Bayes networks often possess a fine independence structure not evident from the topology, but apparent in local conditional distributions. Independence-based (IB) assignments, originally proposed as a theory of abduction, take advantage of such independence, and thus contain fewer assigned variables - and more probability mass. We present several algorithms that use IB assignments for approximating marginal probabilities. Experimental results suggest that this approach is feasible for highly connected belief networks.

Original languageEnglish
Pages (from-to)25-54
Number of pages30
JournalInternational Journal of Approximate Reasoning
Volume14
Issue number1
DOIs
StatePublished - 1 Jan 1996

Keywords

  • Anytime algorithms
  • Approximate belief updating
  • Approximating marginal probabilities
  • Bayesian belief networks
  • Probabilistic reasoning

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Applied Mathematics
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Exploiting case-based independence for approximating marginal probabilities'. Together they form a unique fingerprint.

Cite this