English

Higher-arity PAC learning, VC dimension and packing lemma

Machine Learning 2025-10-16 v2 Discrete Mathematics Machine Learning Combinatorics Logic Statistics Theory Statistics Theory

Abstract

The aim of this note is to overview some of our work in Chernikov, Towsner'20 (arXiv:2010.00726) developing higher arity VC theory (VCn_n dimension), including a generalization of Haussler packing lemma, and an associated tame (slice-wise) hypergraph regularity lemma; and to demonstrate that it characterizes higher arity PAC learning (PACn_n learning) in nn-fold product spaces with respect to product measures introduced by Kobayashi, Kuriyama and Takeuchi'15. We also point out how some of the recent results in arXiv:2402.14294, arXiv:2505.15688, arXiv:2509.20404 follow from our work in arXiv:2010.00726.

Cite

@article{arxiv.2510.02420,
  title  = {Higher-arity PAC learning, VC dimension and packing lemma},
  author = {Artem Chernikov and Henry Towsner},
  journal= {arXiv preprint arXiv:2510.02420},
  year   = {2025}
}

Comments

v.2. Corrected our presentation of PAC_n learning in the sense of Takeuchi et al. in section 4; and slightly improved the PAC_n learning function in Theorem 6.5 to additionally ensure its properness

R2 v1 2026-07-01T06:14:06.181Z