Learning nearly monotone k-term DNF
This note studies the learnability of the class k-term DNF with a bounded number of negations per term. We study the case of learning with membership queries alone, and give tight upper and lower bounds on the number of negations that makes the learning task feasible. We also prove a negative result for equivalence queries. Finally, we show that a slight modification in our algorithm proves that the considered class is also learnable in the Simple PAC model, extending Li and Vitányi result for monotone k-term DNF.
Unable to display preview. Download preview PDF.
- [Ang87a]D. Angluin. “Learning k-term DNF formulas using queries and counterexamples”. Technical Report YALEU/DCS/RR-559, Yale University, August 1987.Google Scholar
- [Ang87b]D. Angluin. “Learning regular sets from queries and counterexamples”. Information and Computation, 75:87–106, November 1987.Google Scholar
- [Ang88]D. Angluin. “Queries and concept learning”. Machine Learning, 2(4):319–342, 1988.Google Scholar
- [Ber93]Ulf Berggren. “Linear Time Deterministic Learning of k-term DNF” In Proc. 6th Annu. Workshop on Comput. Learning Theory, pages 37–40. ACM Press, New York, NY, 1993.Google Scholar
- [Bsh95]N. Bshouty. “Simple Learning Algorithms Using Divide and Conquer”. In Proc. of 8th Annu. ACM Workshop on Comput. Learning Theory, pages 447–453, 1995.Google Scholar
- [BC+95]N. Bshouty, R. Cleve, R. Gavaldà, S. Kannan, and C. Tamon. “Oracles and queries that are sufficient for exact learning”. Journal of Computer and System Sciences, 52, pp. 421–433, 1996.Google Scholar
- [BGHM93]N. Bshouty, S. Goldman, T. Hancock, and S. Matar. “Asking queries to minimize errors”. In Proc. 6th Annu. Workshop on Comput. Learning Theory, pages 41–50. ACM Press, New York, NY, 1993.Google Scholar
- [LV91]M. Li and P. Vitányi. “Learning simple concepts under simple distributions”. SIAM Journal of Computing 20, pages 911–935, 1991.Google Scholar