English

Sample compression schemes for VC classes

Machine Learning 2015-04-15 v2

Abstract

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 kk means that given an arbitrary list of labeled examples, one can retain only kk 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 CC with VC dimension dd has a sample compression scheme of size exponential in dd. 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.

Keywords

Cite

@article{arxiv.1503.06960,
  title  = {Sample compression schemes for VC classes},
  author = {Shay Moran and Amir Yehudayoff},
  journal= {arXiv preprint arXiv:1503.06960},
  year   = {2015}
}

Comments

14 pages. The previous version of this text contained an error; Theorem 2.1 in it is false. This error only affects the statement for multi-labeled classes, and the construction for binary-labeled classes still holds. In the new version of the text, we added a relevant discussion in Section 4

R2 v1 2026-06-22T09:00:29.487Z