BriefGPT.xyz
Jul, 2015
PAC学习的最优样本复杂度
The Optimal Distribution-Free Sample Complexity of Distribution-Dependent Learning
HTML
PDF
Steve Hanneke
TL;DR
通过对Hans Simon最新成果的技术和分析，本文在可实现情况下建立了一个新的PAC学习样本数量的上限，该上限匹配了已知的下限，解决了一个长期存在的开放性问题。
Abstract
This work establishes a new
upper bound
on the worst-case number of labeled samples sufficient for
pac learning
in the
realizable case
, if
→