arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1503.06960cs.LG
收藏

VC类的样本压缩方案

Sample compression schemes for VC classes

Technion-IIT(以色列理工学院);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Shay Moran, Amir Yehudayoff

摘要:

样本压缩方案由Littlestone和Warrant(1986)定义为许多学习算法的基础结构的抽象。粗略地说,大小为$k$的样本压缩方案意味着给定任意一个标记样本列表,可以以允许恢复列表中所有其他样本的标记的方式仅保留其中的$k$。他们表明,压缩意味着二进制标记类的PAC可学习性,并询问另一个方向是否成立。我们回答了他们的问题,并证明了每个VC维为$d$的概念类$C$在$d$中都有一个大小指数的样本压缩方案。证明使用近似极小极大现象的二元矩阵的低VC维,这可能是感兴趣的博弈论的背景下。

英文摘要:

Sample compression schemes were defined by Littlestone and Warmuth (1986) as an abstraction of the structure underlying many learning algorithms. Roughly speaking, a sample compression scheme of size $k$ means that given an arbitrary list of labeled examples, one can retain only $k$ of them in a way that allows to recover the labels of all other examples in the list. They showed that compression implies PAC learnability for binary-labeled classes, and asked whether the other direction holds. We answer their question and show that every concept class $C$ with VC dimension $d$ has a sample compression scheme of size exponential in $d$. The proof uses an approximate minimax phenomenon for binary matrices of low VC dimension, which may be of interest in the context of game theory.

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。

↑