loading...
Learning DNF from Random Walks
Cambridge, Massachusettes October 11-October 14
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/SFCS.2003.123819344th Annual IEEE Symposium on Foundat ...
 This Article 
 
PDF
HTML
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Nader Bshouty, Technion
Elchanan Mossel, University of California at Berkeley
Ryan O?Donnell, Institute for Advanced Study
Rocco A. Servedio, Columbia University
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.
Citation:
Nader Bshouty, Elchanan Mossel, Ryan O?Donnell, Rocco A. Servedio, "Learning DNF from Random Walks," focs, pp.189, 44th Annual IEEE Symposium on Foundations of Computer Science (FOCS'03), 2003
Usage of this product signifies your acceptance of the Terms of Use.