Unlabeled compression schemes exceeding the VC-dimension

Dömötör Pálvölgyi, Gábor Tardos

Research output: Contribution to journalArticle

Abstract

In this note we disprove a conjecture of Kuzmin and Warmuth claiming that every family whose VC-dimension is at most d admits an unlabeled compression scheme to a sample of size at most d. We also study the unlabeled compression schemes of the joins of some families and conjecture that these give a larger gap between the VC-dimension and the size of the smallest unlabeled compression scheme for them.

Original languageEnglish
Pages (from-to)102-107
Number of pages6
JournalDiscrete Applied Mathematics
Volume276
DOIs
Publication statusAccepted/In press - Jan 1 2019

    Fingerprint

Keywords

  • Compression schemes
  • Learning theory
  • VC-dimension

ASJC Scopus subject areas

  • Discrete Mathematics and Combinatorics
  • Applied Mathematics

Cite this