Eigen selection in spectral clustering: a theory guided practice
Statistics Theory
2020-06-09 v2 Statistics Theory
Abstract
Based on a Gaussian mixture type model , we derive an eigen selection procedure that improves the usual spectral clustering in high-dimensional settings. Concretely, we derive the asymptotic expansion of the spiked eigenvalues under eigenvalue multiplicity and eigenvalue ratio concentration results, giving rise to the first theory-backed eigen selection procedure in spectral clustering. The resulting eigen-selected spectral clustering (ESSC) algorithm enjoys better stability and compares favorably against canonical alternatives. We demonstrate the advantages of ESSC using extensive simulation and multiple real data studies.
Keywords
Cite
@article{arxiv.2004.06296,
title = {Eigen selection in spectral clustering: a theory guided practice},
author = {Xiao Han and Xin Tong and Yingying Fan},
journal= {arXiv preprint arXiv:2004.06296},
year = {2020}
}