Paper ID: 2111.14630

On computable learning of continuous features

Nathanael Ackerman, Julian Asilis, Jieqi Di, Cameron Freer, Jean-Baptiste Tristan

We introduce definitions of computable PAC learning for binary classification over computable metric spaces. We provide sufficient conditions for learners that are empirical risk minimizers (ERM) to be computable, and bound the strong Weihrauch degree of an ERM learner under more general conditions. We also give a presentation of a hypothesis class that does not admit any proper computable PAC learner with computable sample function, despite the underlying class being PAC learnable.

Submitted: Nov 24, 2021