Abstract
Let X be a set and \({\mathcal H}\) a collection of functions from X to \(\{0,1\}\). We say that \({\mathcal H}\) shatters a finite set \(C \subset X\) if the restriction of \({\mathcal H}\) yields every possible function from C to \(\{0,1\}\). The VC-dimension of \({\mathcal H}\) is the largest number d such that there exists a set of size d shattered by \({\mathcal H}\), and no set of size \(d+1\) is shattered by \({\mathcal H}\). Vapnik and Chervonenkis introduced this idea in the early 70s in the context of learning theory, and this idea has also had a significant impact on other areas of mathematics. In this paper we study the VC-dimension of a class of functions \({\mathcal H}\) defined on \({\mathbb F}_q^d\), the d-dimensional vector space over the finite field with q elements. Define
where for \(x\in {\mathbb F}_q^d\), \(h_y(x)=1\) if \(\Vert x-y\Vert =t\), and 0 otherwise, where here, and throughout, \(\Vert x\Vert =x_1^2+x_2^2+\cdots +x_d^2\). Here \(t\in {\mathbb F}_q\), \(t\ne 0\). Define \({\mathcal H}_t^d(E)\) the same way with respect to \(E \subset {\mathbb F}_q^d\). The learning task here is to find a sphere of radius t centered at some point \(y\in E\) unknown to the learner. The learning process consists of taking random samples of elements of E of sufficiently large size. We are going to prove that when \(d=2\), and \(|E|\geqslant Cq^{{15}/{8}}\), the VC-dimension of \({\mathcal H}^2_t(E)\) is equal to 3. This leads to an intricate configuration problem which is interesting in its own right and requires a new approach.
Similar content being viewed by others
References
Bennett, M., Chapman, J., Covert, D., Hart, D., Iosevich, A., Pakianathan, J.: Long paths in the distance graph over large subsets of vector spaces over finite fields. J. Korean Math. Soc. 53(1), 115–126 (2016)
Grand, N., Iosevich, A., Juvekar, M., Mayeli, A., McDonald, B., Sun, M., Whybra, N., Wyman, E.: VC-dimension, distances, dot products, and configurations in \({\mathbb{F}}_q^d\). (in preparation)
Iosevich, A., Parshall, H.: Embedding distance graphs in finite field vector spaces. J. Korean Math. Soc. 56(6), 1515–1528 (2019)
Iosevich, A., Rudnev, M.: Erdős distance problem in vector spaces over finite fields. Trans. Am. Math. Soc. 359(12), 6127–6142 (2007)
Shalev-Shwartz, S., Ben-David, S.: Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, Cambridge (2014)
Author information
Authors and Affiliations
Corresponding author
Additional information
Editor in Charge: János Pach
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The author A. Iosevich’s research was supported in part by the National Science Foundation Grant No. HDR TRIPODS - 1934962. The author E. Wyman’s research was supported in part by the 2021 Simons Travel Grant.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fitzpatrick, D., Iosevich, A., McDonald, B. et al. The VC-Dimension and Point Configurations in \({\mathbb F}_q^2\). Discrete Comput Geom 71, 1167–1177 (2024). https://doi.org/10.1007/s00454-023-00570-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00454-023-00570-5