Multiway Spectral Clustering: A Margin-Based Perspective
Abstract
Spectral clustering is a broad class of clustering procedures in which an intractable combinatorial optimization formulation of clustering is "relaxed" into a tractable eigenvector problem, and in which the relaxed solution is subsequently "rounded" into an approximate discrete solution to the original problem. In this paper we present a novel margin-based perspective on multiway spectral clustering. We show that the margin-based perspective illuminates both the relaxation and rounding aspects of spectral clustering, providing a unified analysis of existing algorithms and guiding the design of new algorithms. We also present connections between spectral clustering and several other topics in statistics, specifically minimum-variance clustering, Procrustes analysis and Gaussian intrinsic autoregression.
Cite
@article{arxiv.1102.3768,
title = {Multiway Spectral Clustering: A Margin-Based Perspective},
author = {Zhihua Zhang and Michael I. Jordan},
journal= {arXiv preprint arXiv:1102.3768},
year = {2011}
}
Comments
Published in at http://dx.doi.org/10.1214/08-STS266 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)