Simple PAC learning of simple decision lists
We prove that log n-decision lists — the class of decision lists such that all their terms have low Kolmogorov complexity— are learnable in the simple PAG learning model. The proof is based on a transformation from an algorithm based on equivalence queries (found independently by Simon). Then we introduce the class of simple decision lists, and extend our algorithm to show that simple decision lists are simple-PAC learnable as well. This last result is relevant in that it is, to our knowledge, the first learning algorithm for decision lists in which an exponentially wide set of functions may be used for the terms.
Unable to display preview. Download preview PDF.
- 2.Angluin, D.: Queries and concept learning. Machine Learning 2 (1988) 319–342Google Scholar
- 3.Castro, J.: A note on learning decision lists. Report de Recerca LSI-95-2-R, Dept. LSI, UPC (1995)Google Scholar
- 4.Li, M. and Vitányi, P.: Learning simple concepts under simple distributions. SIAM Journal of Computing 20 (1991) 911–935Google Scholar
- 5.Li, M. and Vitányi, P.: An introduction to Kolmogorov complexity and its applications. Springer-Verlag (1993)Google Scholar
- 6.Rivest, R.: Learning decision lists. Machine Learning 2 (1987) 229–246Google Scholar
- 7.Simon, H.U.: Learning decision lists an trees with equivalence queries. In Second European Conference, EuroCOLT'95, Barcelona (1995) 322–336. Lecture Notes in Artificial Intelligence.Google Scholar