On computable learning of continuous features
Machine Learning
2021-11-30 v1 Logic in Computer Science
Logic
Machine Learning
Abstract
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.
Cite
@article{arxiv.2111.14630,
title = {On computable learning of continuous features},
author = {Nathanael Ackerman and Julian Asilis and Jieqi Di and Cameron Freer and Jean-Baptiste Tristan},
journal= {arXiv preprint arXiv:2111.14630},
year = {2021}
}
Comments
16 pages