On strong consistency of kernel k-means: A Rademacher complexity approach

Article Type

Research Article

Publication Title

Statistics and Probability Letters

Abstract

We provide uniform concentration bounds on the kernel k-means clustering objective based on Rademacher complexity by posing the underlying problem as a risk minimization task. This approach results in state-of-the-art convergence rates on the excess risk besides the eventual establishment of strong consistency of cluster centers.

DOI

10.1016/j.spl.2021.109291

Publication Date

3-1-2022

This document is currently not available here.

Share

COinS