An O(nlog log n) Learning Algorithm for DNF under the Uniform Distribution

Y. Mansour*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We show that a DNF with terms of size at most d can be approximated by a function at most dO(d log 1/ε{lunate}), nonzero Fourier coefficients such that the expected error squared, with respect to the uniform distribution, is at most ε{lunate}. This property is used to derive a learning algorithm for DNF, under the uniform distribution. The learning algorithm uses queries and learns, with respect to the uniform distribution, a DNF with terms of size at most d in time polynomial in n and dO(d log 1/ε{lunate}). The interesting implications are for the case when epsilon is constant. In this case our algorithm learns a DNF with a polynomial number of terms in time nO(log log n), and a DNF with terms of size at most O(log n/log log n) in polynomial time.

Original languageEnglish
Pages (from-to)543-550
Number of pages8
JournalJournal of Computer and System Sciences
Volume50
Issue number3
DOIs
StatePublished - Jun 1995

Fingerprint

Dive into the research topics of 'An O(nlog log n) Learning Algorithm for DNF under the Uniform Distribution'. Together they form a unique fingerprint.

Cite this