Convergence Properties of the K-Means Algorithms
by
Léon Bottou
,
Yoshua Bengio
| Citations: | 66 - 2 self |
BibTeX
@MISC{Bottou_convergenceproperties,
author = {Léon Bottou and Yoshua Bengio},
title = {Convergence Properties of the K-Means Algorithms },
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper studies the convergence properties of the well known K-Means clustering algorithm. The K-Means algorithm can be described either as a gradient descent algorithm or by slightly extending the mathematics of the EM algorithm to this hard threshold case. We show that the K-Means algorithm actually minimizes the quantization error using the very fast Newton algorithm.
