Efficiently Learning Adversarially Robust Halfspaces with Noise

Omar Montasser; Surbhi Goel; Ilias Diakonikolas; Nathan Srebro

Efficiently Learning Adversarially Robust Halfspaces with Noise

Machine Learning 2020-05-18 v1 Data Structures and Algorithms Machine Learning

Authors: Omar Montasser , Surbhi Goel , Ilias Diakonikolas , Nathan Srebro

Abstract

We study the problem of learning adversarially robust halfspaces in the distribution-independent setting. In the realizable setting, we provide necessary and sufficient conditions on the adversarial perturbation sets under which halfspaces are efficiently robustly learnable. In the presence of random label noise, we give a simple computationally efficient algorithm for this problem with respect to any $\ell_p$ -perturbation.

Keywords

computational learning theory adversarial training adversarial robustness

Cite

@article{arxiv.2005.07652,
  title  = {Efficiently Learning Adversarially Robust Halfspaces with Noise},
  author = {Omar Montasser and Surbhi Goel and Ilias Diakonikolas and Nathan Srebro},
  journal= {arXiv preprint arXiv:2005.07652},
  year   = {2020}
}

Related papers

View all related →