Unlabeled sample compression schemes and corner peelings for ample and maximum classes

Victor Chepoi, Shay Moran, Manfred K. Warmuth, Jérémie Chalopin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We examine connections between combinatorial notions that arise in machine learning and topological notions in cubical/simplicial geometry. These connections enable to export results from geometry to machine learning. Our first main result is based on a geometric construction by H. Tracy Hall (2004) of a partial shelling of the cross-polytope which can not be extended. We use it to derive a maximum class of VC dimension 3 that has no corners. This refutes several previous works in machine learning from the past 11 years. In particular, it implies that the previous constructions of optimal unlabeled compression schemes for maximum classes are erroneous. On the positive side we present a new construction of an optimal unlabeled compression scheme for maximum classes. We leave as open whether our unlabeled compression scheme extends to ample (a.k.a. lopsided or extremal) classes, which represent a natural and far-reaching generalization of maximum classes. Towards resolving this question, we provide a geometric characterization in terms of unique sink orientations of the 1-skeletons of associated cubical complexes.

Original languageEnglish
Title of host publication46th International Colloquium on Automata, Languages, and Programming, ICALP 2019
EditorsChristel Baier, Ioannis Chatzigiannakis, Paola Flocchini, Stefano Leonardi
ISBN (Electronic)9783959771092
DOIs
StatePublished - 1 Jul 2019
Externally publishedYes
Event46th International Colloquium on Automata, Languages, and Programming, ICALP 2019 - Patras, Greece
Duration: 9 Jul 201912 Jul 2019

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume132

Conference

Conference46th International Colloquium on Automata, Languages, and Programming, ICALP 2019
Country/TerritoryGreece
CityPatras
Period9/07/1912/07/19

Keywords

  • Ample/extremal class
  • Corner peeling
  • Maximum class
  • Sample compression
  • Sandwich lemma
  • Sauer-Shelah-Perles lemma
  • Unique sink orientation
  • VC-dimension

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint

Dive into the research topics of 'Unlabeled sample compression schemes and corner peelings for ample and maximum classes'. Together they form a unique fingerprint.

Cite this