arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09009cs.LGstat.MEstat.ML
收藏

线性回归的可证训练集

Provable Training Set Debugging for Linear Regression

University of Wisconsin-Madison(威斯康星大学麦迪逊分校);University of Cambridge(剑桥大学)

Xiaomin Zhang, Xiaojin Zhu, Po-Ling Loh

摘要:

我们调查的问题,惩罚$M$估计,启发应用程序在机器学习调试。从两个池中收集数据,一个包含可能被污染的标签的数据,另一个已知仅包含干净标记的点。我们首先制定了一个通用的统计算法,用于识别错误点,并提供严格的理论保证的假设下,数据遵循线性模型。然后,我们提出了两个案例研究来说明我们的一般理论的结果和我们的估计干净与缺陷点的依赖。我们进一步提出了一个算法,调整我们的Lasso算法的参数选择,并提供相应的理论保证。最后,我们考虑一个两个人的“游戏”之间的错误发生器和调试器,调试器可以增加污染的数据集与干净的标记版本的点在原始数据池。我们建立了一个理论上的结果,显示了一个充分条件下,错误生成器总是可以欺骗调试器。尽管如此,我们提供的实证结果表明,这种情况可能不会发生在实践中,使自然增强策略结合我们的Lasso调试算法成功。

英文摘要:

We investigate problems in penalized $M$-estimation, inspired by applications in machine learning debugging. Data are collected from two pools, one containing data with possibly contaminated labels, and the other which is known to contain only cleanly labeled points. We first formulate a general statistical algorithm for identifying buggy points and provide rigorous theoretical guarantees under the assumption that the data follow a linear model. We then present two case studies to illustrate the results of our general theory and the dependence of our estimator on clean versus buggy points. We further propose an algorithm for tuning parameter selection of our Lasso-based algorithm and provide corresponding theoretical guarantees. Finally, we consider a two-person "game" played between a bug generator and a debugger, where the debugger can augment the contaminated data set with cleanly labeled versions of points in the original data pool. We establish a theoretical result showing a sufficient condition under which the bug generator can always fool the debugger. Nonetheless, we provide empirical results showing that such a situation may not occur in practice, making it possible for natural augmentation strategies combined with our Lasso debugging algorithm to succeed.

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。

↑