arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.00922math.STstat.TH
收藏

VC类的局部化:超越局部Rademacher复杂性

Localization of VC Classes: Beyond Local Rademacher Complexities

Nikita Zhivotovskiy, Steve Hanneke

摘要:

在本文中,我们介绍了一种替代本地化的方法,导致了一种新的复杂性措施:不动点的本地经验熵。我们表明,这种复杂性的措施给出了严格的控制复杂性的上界。我们的结果伴随着一个新的极大极小下界,涉及相同的数量。特别是,我们实际上回答的最优性问题的ERM下有界噪声一般VC类。

英文摘要:

In this paper we introduce an alternative localization approach for binary classification that leads to a novel complexity measure: fixed points of the local empirical entropy. We show that this complexity measure gives a tight control over complexity in the upper bounds. Our results are accompanied by a novel minimax lower bound that involves the same quantity. In particular, we practically answer the question of optimality of ERM under bounded noise for general VC classes.

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。

↑