English

VC Classes are Adversarially Robustly Learnable, but Only Improperly

Machine Learning 2019-07-04 v2 Machine Learning

Abstract

We study the question of learning an adversarially robust predictor. We show that any hypothesis class H\mathcal{H} with finite VC dimension is robustly PAC learnable with an improper learning rule. The requirement of being improper is necessary as we exhibit examples of hypothesis classes H\mathcal{H} with finite VC dimension that are not robustly PAC learnable with any proper learning rule.

Keywords

Cite

@article{arxiv.1902.04217,
  title  = {VC Classes are Adversarially Robustly Learnable, but Only Improperly},
  author = {Omar Montasser and Steve Hanneke and Nathan Srebro},
  journal= {arXiv preprint arXiv:1902.04217},
  year   = {2019}
}

Comments

COLT 2019 Camera Ready

R2 v1 2026-06-23T07:38:20.055Z