A Two-Stage Active Learning Algorithm for k-Nearest Neighbors
share
We introduce a simple and intuitive two-stage active learning algorithm for the training of k-nearest neighbors classifiers. We provide consistency guarantees for a modified k-nearest neighbors classifier trained on samples acquired via our scheme, and show that when the conditional probability function ℙ(Y=y|X=x) is sufficiently smooth and the Tsybakov noise condition holds, our actively trained classifiers converge to the Bayes optimal classifier at a faster asymptotic rate than passively trained k-nearest neighbor classifiers.
READ FULL TEXT