The Optimal Sample Complexity of PAC Learning

07/02/2015

∙

by   Steve Hanneke, et al.

∙

0

∙

share

This work establishes a new upper bound on the number of samples sufficient for PAC learning in the realizable case. The bound matches known lower bounds up to numerical constant factors. This solves a long-standing open problem on the sample complexity of PAC learning. The technique and analysis build on a recent breakthrough by Hans Simon.