通过分离连接决策树的可解释性和鲁棒性
Connecting Interpretability and Robustness in Decision Trees through Separation
摘要：
最近的研究已经认识到可解释性和鲁棒性作为可信分类的基本属性。奇怪的是，鲁棒性和可解释性之间的联系是经验性的，但其背后的理论推理仍然难以捉摸。在本文中，我们严格调查这种联系。具体来说，我们专注于解释使用决策树和鲁棒性$l_{\infty}$扰动。以前的作品定义的概念，$r$ -分离的鲁棒性的充分条件。我们证明了树的大小的上限和下限的情况下，数据是$r$分离。然后，我们表明，一个更严格的约束的大小是可能的，当数据是线性分离的。我们提供的第一个算法的鲁棒性，可解释性和准确性的背景下，决策树的可证明的保证。实验证实，我们的算法产生的分类器，是可解释的和强大的，并具有较高的准确性。实验代码可在https://github.com/yangarbiter/interpretable-robust-trees上获得。
英文摘要：
Recent research has recognized interpretability and robustness as essential properties of trustworthy classification. Curiously, a connection between robustness and interpretability was empirically observed, but the theoretical reasoning behind it remained elusive. In this paper, we rigorously investigate this connection. Specifically, we focus on interpretation using decision trees and robustness to $l_{\infty}$-perturbation. Previous works defined the notion of $r$-separation as a sufficient condition for robustness. We prove upper and lower bounds on the tree size in case the data is $r$-separated. We then show that a tighter bound on the size is possible when the data is linearly separated. We provide the first algorithm with provable guarantees both on robustness, interpretability, and accuracy in the context of decision trees. Experiments confirm that our algorithm yields classifiers that are both interpretable and robust and have high accuracy. The code for the experiments is available at https://github.com/yangarbiter/interpretable-robust-trees .
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。
