High-arity Sample Compression

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Coregliano, Leonardo N., Opich, William
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916012475023360
author Coregliano, Leonardo N.
Opich, William
author_facet Coregliano, Leonardo N.
Opich, William
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12465
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle High-arity Sample Compression
Coregliano, Leonardo N.
Opich, William
Machine Learning
Primary: 68Q32
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.
title High-arity Sample Compression
topic Machine Learning
Primary: 68Q32
url https://arxiv.org/abs/2605.12465