On computable learning of continuous features Article Swipe
Related Concepts
Computable function
Computable number
Class (philosophy)
Computable analysis
Metric (unit)
Mathematics
Function (biology)
Sample (material)
Computer science
Pure mathematics
Algebra over a field
Discrete mathematics
Artificial intelligence
Economics
Biology
Operations management
Chemistry
Chromatography
Evolutionary biology
Nathanael Ackerman
,
Julian Asilis
,
Jieqi Di
,
Cameron E. Freer
,
Jean-Baptiste Tristan
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2111.14630
· OA: W3216096655
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2111.14630
· OA: W3216096655
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.
Related Topics
Finding more related topics…