Computable PAC Learning of Continuous Features

Nathanael Ackerman, Julian Asilis, Jieqi Di, Cameron Freer, Jean-Baptiste Tristan
2022 Proceedings of the 37th Annual ACM/IEEE Symposium on Logic in Computer Science  
We introduce definitions of computable PAC learning for binary classification over computable metric spaces. We provide sufficient conditions on a hypothesis class to ensure than an empirical risk minimizer (ERM) is computable, and bound the strong Weihrauch degree of an ERM 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.
doi:10.1145/3531130.3533330 fatcat:uosarl2vtjbh5g2hubkryi4fhi