We consider the sample complexity of learning with adversarial robustness. Most prior theoretical results for this problem have considered a setting where different classes in the data are close together or overlapping. Motivated by some real applications, we consider, in contrast, the well-separated case where there exists a classifier with perfect accuracy and robustness, and show that the sample complexity narrates an entirely different story. Specifically, for linear classifiers, we show a large class of well-separated distributions where the expected robust loss of any algorithm is at least $\Omega(\frac{d}{n})$, whereas the max margin algorithm has expected standard loss $O(\frac{1}{n})$. This shows a gap in the standard and robust losses that cannot be obtained via prior techniques. Additionally, we present an algorithm that, given an instance where the robustness radius is much smaller than the gap between the classes, gives a solution with expected robust loss is $O(\frac{1}{n})$. This shows that for very well-separated data, convergence rates of $O(\frac{1}{n})$ are achievable, which is not the case otherwise. Our results apply to robustness measured in any $\ell_p$ norm with $p > 1$ (including $p = \infty$).
翻译:我们用对抗性强力来考虑学习的抽样复杂性。 这个问题的大多数先前理论结果都考虑过数据中不同类别相近或重叠的设置。 受一些真实应用的驱动, 我们考虑的是, 与此形成对比的是, 在存在一个完全准确和稳健的分类器的情况下, 仔细分离的个案, 并表明样本复杂度是一个完全不同的故事。 具体地说, 对于线性分类器来说, 我们展示了一大批分离的分布, 其中任何算法的预期强值损失至少为$\Omega( frac{ d ⁇ n}$, 而最大差值算法则预计有标准损失$(\ frac{ 1 ⁇ n} 。 这显示了标准损失中存在差距, 并且无法通过先前的技术获得。 此外, 我们提出了一个算法, 如果坚固度半径远小于各个类别之间的差值, 我们的预期稳健损失的解决方案是$( frafc{ 1 ⁇ n}。 这显示, 对于非常稳妥的数据来说, $的趋同率是无法实现的。 $( corrence_ groprity_ pration) a custality) exus a case (c_ pus in custate) unalate) a cas in ac_ a cas axus.