arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.01086stat.MLcs.LG
收藏

鲁棒分类中的计算限制和双赢结果

Computational Limitations in Robust Classification and Win-Win Results

Akshay Degwekar, Preetum Nakkiran, Vinod Vaikuntanathan

摘要:

我们继续研究学习鲁棒分类器中的统计/计算权衡,遵循Bubeck,Lee,Price和Razenshteyn最近的工作,他们展示了分类任务的例子,其中(a)在小扰动状态下存在有效的鲁棒分类器;(b)可以有效地学习非鲁棒分类器;但是(c)在计算上很难学习鲁棒的分类器,假设很难分解大的数字。是否存在一个强大的分类器,他们的任务在大扰动制度的问题似乎与重要的开放问题,在计算数论。在这项工作中,我们在三个方向上扩展了他们的工作。首先,我们展示了计算高效的鲁棒分类是不可能的分类任务,即使存在计算无界的鲁棒分类器。为此,我们依赖于平均情况硬函数的存在性。其次,我们展示了在大扰动状态下难以鲁棒学习的分类任务。也就是说,我们表明,即使存在一个有效的分类器,是强大的大扰动,它是很难计算学习任何非平凡的强大的分类器。我们的第一个构造依赖于单向函数的存在,第二个构造依赖于学习奇偶性与噪声问题的难度。在后一种设置中,不仅存在非鲁棒分类器,而且存在一种有效的算法,该算法在获得多项式多个训练样本的情况下生成新鲜的新标记样本(被Kearns et.(1994))。第三,我们表明,任何这样的反例意味着存在的密码原语,如单向函数。这将我们引向一个双赢的场景:要么我们可以学习一个高效的鲁棒分类器,要么我们可以构建新的加密原语实例。

英文摘要:

We continue the study of statistical/computational tradeoffs in learning robust classifiers, following the recent work of Bubeck, Lee, Price and Razenshteyn who showed examples of classification tasks where (a) an efficient robust classifier exists, in the small-perturbation regime; (b) a non-robust classifier can be learned efficiently; but (c) it is computationally hard to learn a robust classifier, assuming the hardness of factoring large numbers. The question of whether a robust classifier for their task exists in the large perturbation regime seems related to important open questions in computational number theory. In this work, we extend their work in three directions. First, we demonstrate classification tasks where computationally efficient robust classification is impossible, even when computationally unbounded robust classifiers exist. For this, we rely on the existence of average-case hard functions. Second, we show hard-to-robustly-learn classification tasks in the large-perturbation regime. Namely, we show that even though an efficient classifier that is robust to large perturbations exists, it is computationally hard to learn any non-trivial robust classifier. Our first construction relies on the existence of one-way functions, and the second on the hardness of the learning parity with noise problem. In the latter setting, not only does a non-robust classifier exist, but also an efficient algorithm that generates fresh new labeled samples given access to polynomially many training examples (termed as generation by Kearns et. al. (1994)). Third, we show that any such counterexample implies the existence of cryptographic primitives such as one-way functions. This leads us to a win-win scenario: either we can learn an efficient robust classifier, or we can construct new instances of cryptographic primitives.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑