Improved Guarantees for k-means++ and k-means++ Parallel
Machine Learning
2020-10-28 v1 Data Structures and Algorithms
Abstract
In this paper, we study k-means++ and k-means++ parallel, the two most popular algorithms for the classic k-means clustering problem. We provide novel analyses and show improved approximation and bi-criteria approximation guarantees for k-means++ and k-means++ parallel. Our results give a better theoretical justification for why these algorithms perform extremely well in practice. We also propose a new variant of k-means++ parallel algorithm (Exponential Race k-means++) that has the same approximation guarantees as k-means++.
Keywords
Cite
@article{arxiv.2010.14487,
title = {Improved Guarantees for k-means++ and k-means++ Parallel},
author = {Konstantin Makarychev and Aravind Reddy and Liren Shan},
journal= {arXiv preprint arXiv:2010.14487},
year = {2020}
}