acceptodds
Published as a conference paper at NeurIPS 2026

High-arity Sample Compression

Leonardo Coregliano, William Opich

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.

Related papers

See more related submissions when the market opens.