Efficiently Learning Adversarially Robust Halfspaces with Noise

ICML 2020

Efficiently Learning Adversarially Robust Halfspaces with Noise

Jul 12, 2020
|
38 views
|
Details
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. Speakers: Omar Montasser, Surbhi Goel, Ilias Diakonikolas, Nati Srebro

Comments
loading...