An upper bound on the asymptotic error probability on the k-nearest neighbor rule for multiple classes (Corresp.)

  • Authors:

  • L. Gyorfi;Z. Gyorfi

  • Affiliations:

  • -;-

  • Venue:
  • IEEE Transactions on Information Theory
  • Year:
  • 2006

Quantified Score

Hi-index 754.84

Visualization

Abstract

IfR_{k}, denotes the asymptotic error probability of thek- nearest neighbor rule forMclasses andRastdenotes the Bayes probability of error, then conditions are given that yieldR_{k} - Rast leq sqrt{MR{1}/k}.