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

1 July 1978

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory

Vol. 24 (4) , 512-514
https://doi.org/10.1109/tit.1978.1055900

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}.

Keywords

This publication has 4 references indexed in Scilit:

Distribution-free exponential error bound for nearest neighbor pattern classification
IEEE Transactions on Information Theory, 1975
Convergence of the nearest neighbor rule
IEEE Transactions on Information Theory, 1971
Estimation by the nearest neighbor rule
IEEE Transactions on Information Theory, 1968
Nearest neighbor pattern classification
IEEE Transactions on Information Theory, 1967