The VC-dimension and point configurations in ${\Bbb F}_q^2$
D. Fitzpatrick, A. Iosevich, B. McDonald, E. Wyman

TL;DR
This paper investigates the VC-dimension of a class of functions related to point configurations in finite fields, establishing that for certain conditions in two dimensions, the VC-dimension is exactly three.
Contribution
The paper proves that for a subset of the plane over a finite field with sufficiently large size, the VC-dimension of sphere indicator functions is exactly three, introducing a new approach to this configuration problem.
Findings
VC-dimension equals 3 for large enough subsets in ${f F}_q^2$
Establishes a threshold size for the set E
Introduces a new method for analyzing point configurations
Abstract
Let be a set and a collection of functions from to . We say that shatters a finite set if the restriction of yields every possible function from to . The VC-dimension of is the largest number such that there exists a set of size shattered by , and no set of size is shattered by . 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 defined on , the -dimensional vector space over the finite field with elements. Define where for , if…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputability, Logic, AI Algorithms · Machine Learning and Algorithms · Coding theory and cryptography
