Efficiently Learning Adversarially Robust Halfspaces with Noise

Omar Montasser, Surbhi Goel, Ilias Diakonikolas, Nathan Srebro
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:7010-7021, 2020.

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 this Paper

BibTeX
@InProceedings{pmlr-v119-montasser20a, title = {Efficiently Learning Adversarially Robust Halfspaces with Noise}, author = {Montasser, Omar and Goel, Surbhi and Diakonikolas, Ilias and Srebro, Nathan}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {7010--7021}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/montasser20a/montasser20a.pdf}, url = {https://proceedings.mlr.press/v119/montasser20a.html}, 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.} }
Endnote
%0 Conference Paper %T Efficiently Learning Adversarially Robust Halfspaces with Noise %A Omar Montasser %A Surbhi Goel %A Ilias Diakonikolas %A Nathan Srebro %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-montasser20a %I PMLR %P 7010--7021 %U https://proceedings.mlr.press/v119/montasser20a.html %V 119 %X 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.
APA
Montasser, O., Goel, S., Diakonikolas, I. & Srebro, N.. (2020). Efficiently Learning Adversarially Robust Halfspaces with Noise. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:7010-7021 Available from https://proceedings.mlr.press/v119/montasser20a.html.

Related Material