Learning DNF from random walks

  • Authors:
  • Nader H. Bshouty;Elchanan Mossel;Ryan O'Donnell;Rocco A. Servedio

  • Affiliations:
  • Department of Computer Science, Technion, USA;Department of Statistics, University of California, Berkeley, USA;Institute for Advanced Study, Princeton, NJ, USA;Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mailcode 0401, NY 10027, USA

  • Venue:
  • Journal of Computer and System Sciences - Special issue: Learning theory 2003
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

We consider a model of learning Boolean functions from examples generated by a uniform random walk on {0,1}^n. We give a polynomial time algorithm for learning decision trees and DNF formulas in this model. This is the first efficient algorithm for learning these classes in a natural passive learning model where the learner has no influence over the choice of examples used for learning.