Abstract
In this paper, we define and study a new notion of stability for the $k$-means clustering scheme building upon the field of quantization of a probability measure. We connect this definition of stability to a geometric feature of the underlying distribution of the data, named absolute margin condition, inspired by recent works on the subject.
Citation
T. Le Gouic. Q. Paris. "A notion of stability for k-means clustering." Electron. J. Statist. 12 (2) 4239 - 4263, 2018. https://doi.org/10.1214/18-EJS1500
