High-arity Sample Compression
Machine Learning
2026-05-15 v2
Abstract
Recently, a series of works have started studying variations of concepts from learning theory for product spaces, which can be collected under the name high-arity learning theory. In this work, we consider a high-arity variant of sample compression schemes and we prove that the existence of a high-arity sample compression scheme of non-trivial quality implies high-arity PAC learnability.
Cite
@article{arxiv.2605.12465,
title = {High-arity Sample Compression},
author = {Leonardo N. Coregliano and William Opich},
journal= {arXiv preprint arXiv:2605.12465},
year = {2026}
}
Comments
29 pages v2: corrected minor typos