Power k-Means Clustering
Abstract
Clustering is a fundamental task in unsupervised machine learning. Lloyd’s 1957 algorithm for k-means clustering remains one of the most widely used due to its speed and simplicity, but the greedy approach is sensitive to initialization and often falls short at a poor solution. This paper explores an alternative to Lloyd’s algorithm that retains its simplicity and mitigates its tendency to get trapped by local minima. Called power k-means, our method embeds the k-means problem in a continuous class of similar, better behaved problems with fewer local minima. Power k-means anneals its way toward the solution of ordinary k-means by way of majorization-minimization (MM), sharing the appealing descent property and low complexity of Lloyd’s algorithm. Further, our method complements widely used seeding strategies, reaping marked improvements when used together as demonstrated on a suite of simulated and real data examples.
BibTeX
@InProceedings{pmlr-v97-xu19a,
title = {Power k-Means Clustering},
author = {Xu, Jason and Lange, Kenneth},
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
pages = {6921--6931},
year = {2019},
editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
volume = {97},
series = {Proceedings of Machine Learning Research},
month = {09--15 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v97/xu19a/xu19a.pdf},
url = {https://proceedings.mlr.press/v97/xu19a.html},
abstract = {Clustering is a fundamental task in unsupervised machine learning. Lloyd’s 1957 algorithm for k-means clustering remains one of the most widely used due to its speed and simplicity, but the greedy approach is sensitive to initialization and often falls short at a poor solution. This paper explores an alternative to Lloyd’s algorithm that retains its simplicity and mitigates its tendency to get trapped by local minima. Called power k-means, our method embeds the k-means problem in a continuous class of similar, better behaved problems with fewer local minima. Power k-means anneals its way toward the solution of ordinary k-means by way of majorization-minimization (MM), sharing the appealing descent property and low complexity of Lloyd’s algorithm. Further, our method complements widely used seeding strategies, reaping marked improvements when used together as demonstrated on a suite of simulated and real data examples.}
}