Tight Lower Bounds on the VC-dimension of Geometric Set Systems - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Journal of Machine Learning Research Année : 2019

Tight Lower Bounds on the VC-dimension of Geometric Set Systems

Mónika Csikós
  • Fonction : Auteur
Nabil Mustafa
Andrey Kupavskii

Résumé

The VC-dimension of a set system is a way to capture its complexity and has been a key parameter studied extensively in machine learning and geometry communities. In this paper, we resolve two longstanding open problems on bounding the VC-dimension of two fundamental set systems: k-fold unions/intersections of half-spaces and the simplices set system. Among other implications, it settles an open question in machine learning that was first studied in the foundational paper of Blumer et al. (1989) as well as by Eisenstat and Angluin (2007) and Johnson (2008).
Fichier principal
Vignette du fichier
kunionlowerbounds.pdf (282.78 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02316979 , version 1 (31-05-2020)

Licence

Paternité

Identifiants

  • HAL Id : hal-02316979 , version 1

Citer

Mónika Csikós, Nabil Mustafa, Andrey Kupavskii. Tight Lower Bounds on the VC-dimension of Geometric Set Systems. Journal of Machine Learning Research, 2019, 20 (81), pp.1-8. ⟨hal-02316979⟩
59 Consultations
236 Téléchargements

Partager

Gmail Facebook X LinkedIn More