arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.03946cs.LGstat.ML
收藏

基于鉴别特征反馈的鲁棒学习

Robust Learning from Discriminative Feature Feedback

University of California, San Diego(加州大学圣地亚哥分校);Ben-Gurion University of the Negev(内盖夫本-古里安大学)

Sanjoy Dasgupta, Sivan Sabato

摘要:

最近的工作介绍了从判别特征反馈中学习的模型,其中人类注释器不仅提供实例的标签,而且还识别突出实例对之间的重要差异的判别特征。结果表明,这样的反馈可以有利于学习,并使得有可能有效地学习一些概念类,否则将是棘手的。然而,这些结果都依赖于完美的注释者反馈。在本文中,我们介绍了一个更现实,更强大的版本的框架,其中注释者被允许犯错误。我们将展示如何在对抗性和随机性环境中通过算法处理此类错误。特别是,我们得到的遗憾界在这两种设置,在一个完美的注释器的情况下,是独立的功能的数量。我们表明,这一结果不能得到一个天真的减少从强大的设置到非强大的设置。

英文摘要:

Recent work introduced the model of learning from discriminative feature feedback, in which a human annotator not only provides labels of instances, but also identifies discriminative features that highlight important differences between pairs of instances. It was shown that such feedback can be conducive to learning, and makes it possible to efficiently learn some concept classes that would otherwise be intractable. However, these results all relied upon perfect annotator feedback. In this paper, we introduce a more realistic, robust version of the framework, in which the annotator is allowed to make mistakes. We show how such errors can be handled algorithmically, in both an adversarial and a stochastic setting. In particular, we derive regret bounds in both settings that, as in the case of a perfect annotator, are independent of the number of features. We show that this result cannot be obtained by a naive reduction from the robust setting to the non-robust setting.

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。

↑