DocumentCode :
1404577
Title :
Validation of 
-Nearest Neighbor Classifiers
Author :
Bax, Eric
Author_Institution :
Yahoo, Pasadena, CA, USA
Volume :
58
Issue :
5
fYear :
2012
fDate :
5/1/2012 12:00:00 AM
Firstpage :
3225
Lastpage :
3234
Abstract :
This paper presents a method to compute probably approximately correct error bounds for k-nearest neighbor classifiers. The method withholds some training data as a validation set to bound the error rate of the holdout classifier that is based on the remaining training data. Then, the method uses the validation set to bound the difference in error rates between the holdout classifier and the classifier based on all training data. The result is a bound on the out-of-sample error rate for the classifier based on all training data.
Keywords :
learning (artificial intelligence); pattern classification; approximately correct error bounds; holdout classifier; k-nearest neighbor classifiers; out-of-sample error rate; training data; Cancer; Error analysis; Machine learning; Training; Training data; Upper bound; Learning systems; machine learning; nearest neighbor; statistical learning; supervised learning;
fLanguage :
English
Journal_Title :
Information Theory, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9448
Type :
jour
DOI :
10.1109/TIT.2011.2180887
Filename :
6111216
Link To Document :
