On Learning Read-k-Satisfy-j DNF

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.

[1]  D. Angluin.  Queries and Concept Learning , 1988 .

[2]  Jeffrey C. Jackson,et al.  An efficient membership-query algorithm for learning DNF with respect to the uniform distribution , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[3]  E. Kushilevitz,et al.  On Learning Visual Concepts and DNF Formulae , 1996 .

[4]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[5]  Dana Angluin,et al.  When won't membership queries help? , 1991, STOC '91.

[6]  Nader H. Bshouty.  Exact Learning Boolean Function via the Monotone Theory , 1995, Inf. Comput..

[7]  H. Aizenstein,et al.  Exact learning of read-twice DNF formulas , 1991, [1991] Proceedings 32nd Annual Symposium of Foundations of Computer Science.

[8]  Roni Khardon.  On Using the Fourier Transform to Learn Disjoint DNF , 1994, Inf. Process. Lett..

[9]  Marek Karpinski,et al.  Learning read-once formulas with queries , 1993, JACM.

[10]  Lisa Hellerstein,et al.  Read-thrice DNF is hard to learn with membership and equivalence queries , 1992, Proceedings., 33rd Annual Symposium on Foundations of Computer Science.

[11]  Yishay Mansour,et al.  Weakly learning DNF and characterizing statistical query learning using Fourier analysis , 1994, STOC '94.

[12]  Mona Singh,et al.  Learning functions of k terms , 1990, COLT '90.

[13]  Thomas R. Hancock,et al.  Learning 2µ DNF Formulas and kµ Decision Trees , 1991, COLT.

[14]  Vijay Raghavan,et al.  Read-Twice DNF Formulas are Properly Learnable , 1994, Inf. Comput..

[15]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[16]  Avrim Blum,et al.  Fast learning of k-term DNF formulas with queries , 1992, STOC '92.

[17]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[18]  Leslie G. Valiant,et al.  On the learnability of Boolean formulae , 1987, STOC.

[19]  Eyal Kushilevitz,et al.  Learning Decision Trees Using the Fourier Spectrum , 1993, SIAM J. Comput..

[20]  Leonard Pitt,et al.  Exact learning of read-k disjoint DNF and not-so-disjoint DNF , 1992, COLT '92.