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 2009.06202cs.LGcs.AIcs.NEmath.STstat.MLstat.TH
收藏

鲁棒深度学习的风险界限

Risk Bounds for Robust Deep Learning

Ruhr-University Bochum(波鸿鲁尔大学)

Johannes Lederer

摘要:

据观察,某些损失函数可以使深度学习管道对数据中的缺陷具有鲁棒性。在本文中,我们支持这些实证研究结果与统计理论。我们特别表明,具有无界、Lipschitz连续损失函数(例如最小绝对偏差损失、Huber损失、Cauchy损失和Tukey双权损失)的经验风险最小化可以在对数据的最小假设下提供有效的预测。更一般地说,我们的论文为深度学习中鲁棒损失函数的好处提供了理论证据。

英文摘要:

It has been observed that certain loss functions can render deep-learning pipelines robust against flaws in the data. In this paper, we support these empirical findings with statistical theory. We especially show that empirical-risk minimization with unbounded, Lipschitz-continuous loss functions, such as the least-absolute deviation loss, Huber loss, Cauchy loss, and Tukey's biweight loss, can provide efficient prediction under minimal assumptions on the data. More generally speaking, our paper provides theoretical evidence for the benefits of robust loss functions in deep learning.

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。

↑