Estimating Average-Case Learning Curves Using Bayesian, Statistical Physics and VC Dimension Methods

David Haussler, Michael Kearns, Manfred Opper, Robert Schapire

Advances in Neural Information Processing Systems 4 (NIPS 1991)

In this paper we investigate an average-case model of concept learning, and give results that place the popular statistical physics and VC dimension theories of learning curve behavior in a common framework.