The Sample Complexity of Learning Fixed-Structure Bayesian Networks

  • Authors:
  • Sanjoy Dasgupta

  • Affiliations:
  • Department of Computer Science, University of California, Berkeley, CA 94720. E-mail: dasgupta@cs.berkeley.edu

  • Venue:
  • Machine Learning - Special issue on learning with probabilistic representations
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

We consider the problem of PAC learning probabilistic networks in the case where the structure of the net is specified beforehand. We allow the conditional probabilities to be represented in anymanner (as tables or specialized functions) and obtain sample complexity bounds for learning nets with and without hidden nodes.