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.
Cite
Text
Montasser et al. "Efficiently Learning Adversarially Robust Halfspaces with Noise." International Conference on Machine Learning, 2020.Markdown
[Montasser et al. "Efficiently Learning Adversarially Robust Halfspaces with Noise." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/montasser2020icml-efficiently/)BibTeX
@inproceedings{montasser2020icml-efficiently,
title = {{Efficiently Learning Adversarially Robust Halfspaces with Noise}},
author = {Montasser, Omar and Goel, Surbhi and Diakonikolas, Ilias and Srebro, Nathan},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {7010-7021},
volume = {119},
url = {https://mlanthology.org/icml/2020/montasser2020icml-efficiently/}
}