Geodesic
Modified classification algorithm of $k$-nearest neighbor type
Fundamentalʹnaâ i prikladnaâ matematika, Tome 6 (2000) no. 2, pp. 533-548 
D. A. Pavlov; A. P. Serykh. Modified classification algorithm of $k$-nearest neighbor type. Fundamentalʹnaâ i prikladnaâ matematika, Tome 6 (2000) no. 2, pp. 533-548. http://geodesic.mathdoc.fr/item/FPM_2000_6_2_a11/
@article{FPM_2000_6_2_a11,
     author = {D. A. Pavlov and A. P. Serykh},
     title = {Modified classification algorithm of $k$-nearest neighbor type},
     journal = {Fundamentalʹna\^a i prikladna\^a matematika},
     pages = {533--548},
     year = {2000},
     volume = {6},
     number = {2},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/FPM_2000_6_2_a11/}
}
TY  - JOUR
AU  - D. A. Pavlov
AU  - A. P. Serykh
TI  - Modified classification algorithm of $k$-nearest neighbor type
JO  - Fundamentalʹnaâ i prikladnaâ matematika
PY  - 2000
SP  - 533
EP  - 548
VL  - 6
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/FPM_2000_6_2_a11/
LA  - ru
ID  - FPM_2000_6_2_a11
ER  - 
%0 Journal Article
%A D. A. Pavlov
%A A. P. Serykh
%T Modified classification algorithm of $k$-nearest neighbor type
%J Fundamentalʹnaâ i prikladnaâ matematika
%D 2000
%P 533-548
%V 6
%N 2
%U http://geodesic.mathdoc.fr/item/FPM_2000_6_2_a11/
%G ru
%F FPM_2000_6_2_a11

Voir la notice de l'article provenant de la source Math-Net.Ru

Excessive amount of calculation restricts possibility of using $k$-nearest neighbor classification algorithms. In this paper a new method of estimation of $k$-nearest neighbor type is proposed. It is based on use of blocks of observed data. It is shown that the new estimator converges in probability. Also, the method based on the new estimator provides the same probability of misclassification as the standard algorithm does. But the new method requires much less calculation.