ABSTRACT
We show that randomly generated c log(n)-DNF formula can be learned exactly in probabilistic polynomial time using randomly generated examples. Our notion of randomly generated is with respect to a uniform distribution.
To prove this we extend the concept of well behaved c log(n)-Monotone DNF formulae to c log(n)-DNF formulae, and show that almost every DNF formula is well-behaved, and that there exists a probabilistic polynomial time algorithm that exactly learns all well behaved c log(n)-DNF formula. This is the first algorithm that properly learns (non-monotone) DNF with a polynomial number of terms from random examples alone.
- H. Aizenstein and L. Pitt. On the learnability of disjunctive normal form formulas. Machine Learning, 19(3):183--208, 1995. Google ScholarDigital Library
- M. Alekhnovich, M. Braverman, V. Feldman, A. R. Klivans, and T. Pitassi. The complexity of properly learning simple concept classes. J. Comput. Syst. Sci., 74(1):16--34, 2008. Google ScholarDigital Library
- A. Blum, M. L. Furst, J. C. Jackson, M. J. Kearns, Y. Mansour, and S. Rudich. Weakly learning dnf and characterizing statistical query learning using fourier analysis. In STOC, pages 253--262, 1994. Google ScholarDigital Library
- U. Feige and J. Kilian. Zero knowledge and the chromatic number. In IEEE Conference on Computational Complexity, pages 278--287, 1996. Google ScholarDigital Library
- V. Feldman. Hardness of approximate two-level logic minimization and pac learning with membership queries. In STOC '06: Proceedings of the thirty-eighth annual ACM symposium on Theory of computing, pages 363--372, New York, NY, USA, 2006. ACM. Google ScholarDigital Library
- T. R. Hancock and Y. Mansour. Learning monotone µ dnf formulas on product distributions. In COLT, pages 179--183, 1991. Google ScholarDigital Library
- J. C. Jackson and R. A. Servedio. On learning random dnf formulas under the uniform distribution. In C. Chekuri, K. Jansen, J. D. P. Rolim, and L. Trevisan, editors, APPROX--RANDOM, volume 3624 of Lecture Notes in Computer Science, pages 342--353. Springer, 2005. Google ScholarDigital Library
- S. Kutin. Extensions to mcdiarmid's inequality when dierences are bounded with high probability. Technical Report TR-2002-04, Department of Computer Science, University of Chicago, 2002.Google Scholar
- C. McDiarmid. On the method of bounded dierences. Surveys in Combinatorics, pages 148--188, 1989.Google Scholar
- K. Pillaipakkamnatt and V. V. Raghavan. On the limits of proper learnability of subclasses of dnf formulas. Machine Learning, 25(2--3):237--263, 1996. Google ScholarDigital Library
- L. Pitt and L. G. Valiant. Computational limitations on learning from examples. J. ACM, 35(4):965--984, 1988. Google ScholarDigital Library
- L. Sellie. Learning random monotone dnf under the uniform distribution. In R. A. Servedio and T. Zhang, editors, COLT, pages 181--192. Omnipress, 2008.Google Scholar
- L. G. Valiant. A theory of the learnable. In STOC, pages 436--445. ACM, 1984. Google ScholarDigital Library
- K. A. Verbeurgt. Learning dnf under the uniform distribution in quasi-polynomial time. In COLT, pages 314--326, 1990. Google ScholarDigital Library
Index Terms
- Exact learning of random DNF over the uniform distribution
Recommendations
Learning DNF from random walks
Special issue: Learning theory 2003We 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 ...
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 ...
Comments