arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.10797cs.LGcs.CRmath.APstat.ML
收藏

对抗分类:必要条件和几何流

Adversarial Classification: Necessary conditions and geometric flows

University of Wisconsin(威斯康星大学);North Carolina State University(北卡罗来纳州立大学)

Nicolas Garcia Trillos, Ryan Murray

摘要:

我们研究了一个版本的对抗性分类,其中对手被授权破坏数据输入到一定的距离$\varepsilon$,使用变分分析工具。特别是,我们描述了必要的条件与最佳的分类受到这样的对手。使用必要的条件,我们推导出一个几何演化方程,该方程可用于跟踪分类边界随着$\varepsilon$变化而发生的变化。这个演化方程在一维可以描述为非耦合的微分方程组,在高维可以描述为平均曲率型方程。在一个维度上,并在温和的假设下的数据分布,我们严格证明,可以使用从$\varepsilon=0$,这是简单的贝叶斯分类器的初始值问题,以解决全球最小值的对抗问题的$\varepsilon$。在更高的维度,我们提供了一个类似的结果,虽然有条件的初值问题的正则解的存在。在证明我们的主要结果的过程中,我们得到了一个独立的利益的结果,连接原始的对抗问题的最优运输问题,在没有假设类是否平衡或不。数值例子说明这些想法也被提出。

英文摘要:

We study a version of adversarial classification where an adversary is empowered to corrupt data inputs up to some distance $\varepsilon$, using tools from variational analysis. In particular, we describe necessary conditions associated with the optimal classifier subject to such an adversary. Using the necessary conditions, we derive a geometric evolution equation which can be used to track the change in classification boundaries as $\varepsilon$ varies. This evolution equation may be described as an uncoupled system of differential equations in one dimension, or as a mean curvature type equation in higher dimension. In one dimension, and under mild assumptions on the data distribution, we rigorously prove that one can use the initial value problem starting from $\varepsilon=0$, which is simply the Bayes classifier, in order to solve for the global minimizer of the adversarial problem for small values of $\varepsilon$. In higher dimensions we provide a similar result, albeit conditional to the existence of regular solutions of the initial value problem. In the process of proving our main results we obtain a result of independent interest connecting the original adversarial problem with an optimal transport problem under no assumptions on whether classes are balanced or not. Numerical examples illustrating these ideas are also presented.

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。

↑