A parallel algorithm for exact bayesian network inference

Olga Nikolova, Jaroslaw Zola, Srinivas Aluru

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

Given n random variables and a set of m observations of each of the n variables, the Bayesian network inference problem is to infer a directed acyclic graph (DAG) on the n variables such that the implied joint probability distribution best explains the set of observations. Bayesian networks are widely used in many fields ranging from data mining to computational biology. Exact inference of Bayesian networks takes O(n2 · 2n) time plus the cost of O(n · 2n) evaluations of an application-specific scoring function. In this paper, we present a parallel algorithm for exact Bayesian inference that is work-optimal and communication-efficient. We demonstrate the applicability of our method by an implementation on the IBM Blue Gene/L, with experimental results that exhibit near perfect scaling.

Original languageEnglish (US)
Title of host publication16th International Conference on High Performance Computing, HiPC 2009 - Proceedings
Pages342-349
Number of pages8
DOIs
StatePublished - 2009
Externally publishedYes
Event16th International Conference on High Performance Computing, HiPC 2009 - Kochi, India
Duration: Dec 16 2009Dec 19 2009

Publication series

Name16th International Conference on High Performance Computing, HiPC 2009 - Proceedings

Conference

Conference16th International Conference on High Performance Computing, HiPC 2009
CountryIndia
CityKochi
Period12/16/0912/19/09

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'A parallel algorithm for exact bayesian network inference'. Together they form a unique fingerprint.

Cite this