English

A notion of stability for k-means clustering

Statistics Theory 2018-03-09 v2 Machine Learning Statistics Theory

Abstract

In this paper, we define and study a new notion of stability for the kk-means clustering scheme building upon the notion of quantization of a probability measure. We connect this notion of stability to a geometric feature of the underlying distribution of the data, named absolute margin condition, inspired by recent works on the subject.

Keywords

Cite

@article{arxiv.1801.09419,
  title  = {A notion of stability for k-means clustering},
  author = {Thibaut Le Gouic and Quentin Paris},
  journal= {arXiv preprint arXiv:1801.09419},
  year   = {2018}
}