Efficiently Learning Adversarially Robust Halfspaces with Noise

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.

References in corpus (2)

• VC Classes are Adversarially Robustly Learnable, but Only Improperly
• On Robustness to Adversarial Examples and Polynomial Optimization

Cited by in corpus (1)

• The Complexity of Adversarially Robust Proper Learning of Halfspaces with Agnostic Noise