The distribution-independent model of concept learning from examples ("PAC-learning") due to Valiant [15] is investigated. It has been shown that the existence of an Occarn algorithm for a class of concepts is a sufficient condition for the PAC-learnability of that class [2, 3]. (An Occam algorithm is a randomized polynomial-time algorithm that, when given as input a sample of strings of some unknown concept to be learned, outputs a small description of a concept that is consistent with the sample.) In this paper it is shown that for all concept classes satisfying a natural closure property the converse is also true; the PAC-learnability of the class implies the existence of an Occam algorithm for the class. This results in a complete combinatorial characterization of the PAC-learnability of a wide variety of concept classes. 1 I n t r o d u c t i o n The distribution-independent model of concept learning (PA C-learning, for "probably approximately correct learning") was introduced by Valiant [15] and has been widely used to investigate the phenomenon of learning from examples (e.g., many of the papers contained in [7] and [12]). In this model a concept is a subset of a domain of elements, and a concept class is a set of such concepts. A learning algorithm is presented with a collection of domain elements, with each element labeled "Suppor ted in par t by NSF grant IRI-8809570. **Supported in past by NSF grant IRL8809570, and by the Depar tment of Compute r Science, Universi ty of Illinois at
[1]
Leslie G. Valiant,et al.
A theory of the learnable
,
1984,
STOC '84.
[2]
David Haussler,et al.
Occam's Razor
,
1987,
Inf. Process. Lett..
[3]
Leslie G. Valiant,et al.
Computational limitations on learning from examples
,
1988,
JACM.
[4]
Leslie G. Valiant,et al.
A general lower bound on the number of examples needed for learning
,
1988,
COLT '88.
[5]
David Haussler,et al.
Equivalence of models for polynomial learnability
,
1988,
COLT '88.
[6]
M. Kearns,et al.
Crytographic limitations on learning Boolean formulae and finite automata
,
1989,
STOC '89.
[7]
David Haussler,et al.
Proceedings of the 1988 Workshop on Computational Learning Theory : MIT, August 3-5, 1988
,
1989
.
[8]
Manfred K. Warmuth.
Towards Representation Independence in PAC Learning
,
1989,
AII.
[9]
Robert H. Sloan,et al.
Computational learning theory: new models and algorithms
,
1989
.
[10]
David Haussler,et al.
Learnability and the Vapnik-Chervonenkis dimension
,
1989,
JACM.