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 2210.05455cs.LGcs.DM
收藏

交闭类和极值类的无标号样本压缩方案

Unlabelled Sample Compression Schemes for Intersection-Closed Classes and Extremal Classes

University of Melbourne(墨尔本大学)

J. Hyam Rubinstein, Benjamin I. P. Rubinstein

摘要:

概念类的样本可压缩性在学习理论中起着重要的作用,作为PAC可学习性的充分条件,最近又作为自适应数据分析中鲁棒泛化的途径。大小为$O(d)$的压缩方案是否必须存在于VC维$d$的所有类中尚不清楚,但Warcourt证实为真。最近,Chalopin,Chepoi,Moran和Warren(2018)给出了一个美丽的未标记样本压缩方案,大小为VC维,适用于所有最大类:满足Sauer-Shelah-Perles引理的类。他们还提供了一个反例,以压缩方案的基础上,一个有前途的方法称为角剥离。本文简化和推广了他们的证明技巧,使之能处理VC维$d$的所谓极值类,它包含VC维$d-1$的极大类.给出了一个标准,这将意味着所有极值类承认大小为$d$的未标记压缩方案。我们还证明了所有VC维$d$的交闭类都允许大小至多为$11d$的未标记压缩方案。

英文摘要:

The sample compressibility of concept classes plays an important role in learning theory, as a sufficient condition for PAC learnability, and more recently as an avenue for robust generalisation in adaptive data analysis. Whether compression schemes of size $O(d)$ must necessarily exist for all classes of VC dimension $d$ is unknown, but conjectured to be true by Warmuth. Recently Chalopin, Chepoi, Moran, and Warmuth (2018) gave a beautiful unlabelled sample compression scheme of size VC dimension for all maximum classes: classes that meet the Sauer-Shelah-Perles Lemma with equality. They also offered a counterexample to compression schemes based on a promising approach known as corner peeling. In this paper we simplify and extend their proof technique to deal with so-called extremal classes of VC dimension $d$ which contain maximum classes of VC dimension $d-1$. A criterion is given which would imply that all extremal classes admit unlabelled compression schemes of size $d$. We also prove that all intersection-closed classes with VC dimension $d$ admit unlabelled compression schemes of size at most $11d$.

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。

↑