Paper ID: 2402.14294

High-arity PAC learning via exchangeability

Leonardo N. Coregliano, Maryanthe Malliaris

We develop a theory of high-arity PAC learning, which is statistical learning in the presence of "structured correlation". In this theory, hypotheses are either graphs, hypergraphs or, more generally, structures in finite relational languages, and i.i.d. sampling is replaced by sampling an induced substructure, producing an exchangeable distribution. Our main theorems establish a high-arity (agnostic) version of the fundamental theorem of statistical learning.

Submitted: Feb 22, 2024