When are epsilon-nets small?
Abstract
In many interesting situations the size of epsilon-nets depends only on together with different complexity measures. The aim of this paper is to give a systematic treatment of such complexity measures arising in Discrete and Computational Geometry and Statistical Learning, and to bridge the gap between the results appearing in these two fields. As a byproduct, we obtain several new upper bounds on the sizes of epsilon-nets that generalize/improve the best known general guarantees. In particular, our results work with regimes when small epsilon-nets of size exist, which are not usually covered by standard upper bounds. Inspired by results in Statistical Learning we also give a short proof of the Haussler's upper bound on packing numbers.
Cite
@article{arxiv.1711.10414,
title = {When are epsilon-nets small?},
author = {Andrey Kupavskii and Nikita Zhivotovskiy},
journal= {arXiv preprint arXiv:1711.10414},
year = {2021}
}
Comments
22 pages; minor changes, accepted version