arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1209.1086cs.LGcs.AIstat.ML
收藏

度量学习的鲁棒性和推广性

Robustness and Generalization for Metric Learning

University of Southern California(南加州大学);Laboratoire Hubert Curien UMR CNRS 5516(于贝尔·居里安实验室(法国国家科学研究中心联合实验室 5516));Université Jean Monnet(让·莫奈大学)

Aurélien Bellet, Amaury Habrard

摘要:

度量学习在过去的十年里引起了人们的极大兴趣,但是这种方法的泛化能力还没有得到深入的研究。在本文中,我们介绍了算法鲁棒性的概念(以前由徐和Mannor介绍),可用于推导度量学习的泛化界。我们进一步表明,一个弱的鲁棒性的概念实际上是一个度量学习算法推广的充分必要条件。为了说明所提出的框架的适用性,我们推导出一个大的家庭现有的度量学习算法,包括一些稀疏的配方,不包括以前的结果的泛化结果。

英文摘要:

Metric learning has attracted a lot of interest over the last decade, but the generalization ability of such methods has not been thoroughly studied. In this paper, we introduce an adaptation of the notion of algorithmic robustness (previously introduced by Xu and Mannor) that can be used to derive generalization bounds for metric learning. We further show that a weak notion of robustness is in fact a necessary and sufficient condition for a metric learning algorithm to generalize. To illustrate the applicability of the proposed framework, we derive generalization results for a large family of existing metric learning algorithms, including some sparse formulations that are not covered by previous results.

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。

↑