论文标题
半监督的对抗性PAC的表征
A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability
论文作者
论文摘要
我们研究学习对抗性稳健的预测因子以测试半监督PAC模型中的时间攻击的问题。我们解决了需要多少个标记和未标记的示例以确保学习的问题。我们表明，拥有足够的未标记数据（与以前的作品相比，标记的样品复杂性可以任意较小，并且具有不同的复杂度度量的特征。我们证明了该样品复杂性上的上限和下限几乎匹配。这表明，即使在最差的无分布模型中，半监督的鲁棒学习也有很大的好处，并在监督和半监督的标签复杂性之间建立了差距，这在标准的非企业PAC学习中不存在。
We study the problem of learning an adversarially robust predictor to test time attacks in the semi-supervised PAC model. We address the question of how many labeled and unlabeled examples are required to ensure learning. We show that having enough unlabeled data (the size of a labeled sample that a fully-supervised method would require), the labeled sample complexity can be arbitrarily smaller compared to previous works, and is sharply characterized by a different complexity measure. We prove nearly matching upper and lower bounds on this sample complexity. This shows that there is a significant benefit in semi-supervised robust learning even in the worst-case distribution-free model, and establishes a gap between the supervised and semi-supervised label complexities which is known not to hold in standard non-robust PAC learning.
