On Learning Read-k-Satisfy-j DNF

Authors:
Howard Aizenstein;Avrim Blum;Roni Khardon;Eyal Kushilevitz;Leonard Pitt;Dan Roth
Affiliations:
-;-;-;-;-;-
Venue:
SIAM Journal on Computing
Year:
1998

Citing 0
Cited 6

Generating all maximal independent sets of bounded-degree hypergraphs

COLT '97 Proceedings of the tenth annual conference on Computational learning theory
Efficient Read-Restricted Monotone CNF/DNF Dualization by Learning with Membership Queries

Machine Learning
On automatic knowledge validation for Bayesian knowledge bases

Data & Knowledge Engineering
Learning unions of ω(1)-dimensional rectangles

Theoretical Computer Science
Learning read-constant polynomials of constant degree modulo composites

CSR'11 Proceedings of the 6th international conference on Computer science: theory and applications
Learning unions of ω(1)-dimensional rectangles

ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory

Quantified Score

Hi-index	0.01

Visualization

Abstract

We study the learnability of read-k-satisfy-j (RkSj) DNF formulas. These are boolean formulas in disjunctive normal form (DNF), in which the maximum number of occurrences of a variable is bounded by k, and the number of terms satisfied by any assignment is at most j. After motivating the investigation of this class of DNF formulas, we present an algorithm that for any unknown RkSj DNF formula to be learned, with high probability finds a logically equivalent DNF formula using the well-studied protocol of equivalence and membership queries. The algorithm runs in polynomial time for $k\cdot j=O({\log n\over\log\log n})$, where n is the number of input variables.