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

László Györfi; Z. Györfi

doi:https://doi.org/10.1109/tit.1978.1055900

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

László Györfi, Z. Györfi · IEEE Transactions on Information Theory · 1978

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

Read the paper · More papers on PaperTik