Efficiently Learning Adversarially Robust Halfspaces with Noise
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:7010-7021, 2020.
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.