Learning DNF From Random Walks
Loading...
Penn collection
Statistics Papers
Degree type
Discipline
Subject
Boolean functions
Fourier analysis
computational complexity
decision trees
learning (artificial intelligence)
Boolean function
DNF
disjunctive normal form
learning decision tree
passive learning model
polynomial time algorithm
random walk
algorithm design and analysis
computer science
decision trees
humans
knowledge representation
learning systems
mathematics
polynomials
statistics
Computer Sciences
Statistics and Probability
Fourier analysis
computational complexity
decision trees
learning (artificial intelligence)
Boolean function
DNF
disjunctive normal form
learning decision tree
passive learning model
polynomial time algorithm
random walk
algorithm design and analysis
computer science
decision trees
humans
knowledge representation
learning systems
mathematics
polynomials
statistics
Computer Sciences
Statistics and Probability
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Bshouty, Nader
Mossel, Elchanan
O'Donnell, Ryan
Servedio, Rocco A
Contributor
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.
Advisor
Date of presentation
2003-10-11
Conference name
Statistics Papers
Conference dates
2023-05-17T15:10:01.000