Skip to yearly menu bar Skip to main content


Poster

Clustering with Bregman Divergences: an Asymptotic Analysis

Chaoyue Liu · Mikhail Belkin

Area 5+6+7+8 #95

Keywords: [ Clustering ] [ Learning Theory ]


Abstract: Clustering, in particular $k$-means clustering, is a central topic in data analysis. Clustering with Bregman divergences is a recently proposed generalization of $k$-means clustering which has already been widely used in applications. In this paper we analyze theoretical properties of Bregman clustering when the number of the clusters $k$ is large. We establish quantization rates and describe the limiting distribution of the centers as $k\to \infty$, extending well-known results for $k$-means clustering.

Live content is unavailable. Log in and register to view live content