A Computability Perspective on (Verified) Machine Learning
Machine Learning
2021-02-15 v1 Logic in Computer Science
Abstract
There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.
Cite
@article{arxiv.2102.06585,
title = {A Computability Perspective on (Verified) Machine Learning},
author = {Tonicha Crook and Jay Morgan and Arno Pauly and Markus Roggenbach},
journal= {arXiv preprint arXiv:2102.06585},
year = {2021}
}