Efficiently Learning Adversarially Robust Halfspaces with Noise
Efficiently Learning Adversarially Robust Halfspaces with Noise
复制标题
DOI：
--
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Omar Montasser;Surbhi Goel;Ilias Diakonikolas;N. Srebro
中科院分区：
文献类型：
--
作者：
Omar Montasser;Surbhi Goel;Ilias Diakonikolas;N. Srebro
研究了分布无关情况下的对抗鲁棒半空间的学习问题。在可实现条件下，给出了半空间有效鲁棒可学习的对抗性摄动集的充分必要条件。在随机标签噪声存在的情况下，对于任意$\ell_p$-扰动，我们给出了一个简单的计算效率高的算法。
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.