A metric entropy bound is not sufficient for learnability
R. M. Dudley, Sanjeev R. Kulkarni, T. Richardson, Ofer Zeitouni · IEEE Transactions on Information Theory · 1994
The authors prove by means of a counterexample that it is not sufficient, for probably approximately correct (PAC) learning under a class of distributions, to have a uniform bound on the metric entropy of the class of concepts to be learned. This settles a conjecture of Benedek and Itai (1991).>