Tech Reports

Tech Report kmi-97-03 Abstract

Efficient Parameter Learning in Bayesian Networks from Incomplete Databases
Techreport ID: kmi-97-03
Date: 1997
Author(s): Marco Ramoni and Paola Sebastiani

Current methods to learn conditional probabilities from incomplete databases use a common strategy: they complete the database by inferring somehow the missing data from the available information and then learn from the completed database. This paper introduces a new method - called bound and collapse (BC) - which does not follow this strategy. BC starts by bounding the set of estimates consistent with the available information and then collapses the resulting set to a point estimate via a convex combination of the extreme points, with weights depending on the assumed pattern of missing data. Experiments comparing c to the Gibbs Samplings are also provided. 1. Knowledge Media Institute, The Open University. 2. Department of Actuarial Science and Statistics, City University.