Efficiently Learning Adversarially Robust Halfspaces with Noise

Omar Montasser · Surbhi Goel · Ilias Diakonikolas · Nati Srebro

Keywords: [ Adversarial Examples ] [ Computational Learning Theory ] [ Learning Theory ] [ Statistical Learning Theory ]

[ Abstract ]
Tue 14 Jul 6 p.m. PDT — 6:45 p.m. PDT
Wed 15 Jul 4 a.m. PDT — 4:45 a.m. PDT

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.

Chat is not available.