Indexability, concentration, and VC theory

  • Authors:
  • Vladimir Pestov

  • Affiliations:
  • University of Ottawa, Ottawa, Ontario, Canada

  • Venue:
  • Proceedings of the Third International Conference on SImilarity Search and APplications
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Degrading performance of indexing schemes for exact similarity search in high dimensions has long since been linked to histograms of distributions of distances and other 1-Lipschitz functions getting concentrated. We discuss this observation in the framework of the phenomenon of concentration of measure on the structures of high dimension and the Vapnik-Chervonenkis theory of statistical learning.