ML Anthology

Convergence Properties of the K-Means Algorithms

Léon Bottou, Yoshua Bengio
NeurIPS 1994 pp. 585-592
/neurips/1994/bottou1994neurips-convergence/

Abstract

This paper studies the convergence properties of the well known K-Means clustering algorithm. The K-Means algorithm can be de(cid:173) scribed either as a gradient descent algorithm or by slightly extend(cid:173) ing 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.

PDF NeurIPS Semantic Scholar

Cite

Text

Bottou and Bengio. "Convergence Properties of the K-Means Algorithms." Neural Information Processing Systems, 1994.

Markdown

[Bottou and Bengio. "Convergence Properties of the K-Means Algorithms." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/bottou1994neurips-convergence/)

BibTeX

@inproceedings{bottou1994neurips-convergence,
  title     = {{Convergence Properties of the K-Means Algorithms}},
  author    = {Bottou, Léon and Bengio, Yoshua},
  booktitle = {Neural Information Processing Systems},
  year      = {1994},
  pages     = {585-592},
  url       = {https://mlanthology.org/neurips/1994/bottou1994neurips-convergence/}
}