Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering

06/29/2018
by   Shuyang Ling, et al.
0

Spectral clustering has become one of the most widely used clustering techniques when the structure of the individual clusters is non-convex or highly anisotropic. Yet, despite its immense popularity, there exists fairly little theory about performance guarantees for spectral clustering. This issue is partly due to the fact that spectral clustering typically involves two steps which complicated its theoretical analysis: first, the eigenvectors of the associated graph Laplacian are used to embed the dataset, and second, k-means clustering algorithm is applied to the embedded dataset to get the labels. This paper is devoted to the theoretical foundations of spectral clustering and graph cuts. We consider a convex relaxation of graph cuts, namely ratio cuts and normalized cuts, that makes the usual two-step approach of spectral clustering obsolete and at the same time gives rise to a rigorous theoretical analysis of graph cuts and spectral clustering. We derive deterministic bounds for successful spectral clustering via a spectral proximity condition that naturally depends on the algebraic connectivity of each cluster and the inter-cluster connectivity. Moreover, we demonstrate by means of some popular examples that our bounds can achieve near-optimality. Our findings are also fundamental for the theoretical understanding of kernel k-means. Numerical simulations confirm and complement our analysis.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/10/2020

A Performance Guarantee for Spectral Clustering

The two-step spectral clustering method, which consists of the Laplacian...
research
05/11/2018

Convex Programming Based Spectral Clustering

Clustering is a fundamental task in data analysis, and spectral clusteri...
research
12/20/2021

Regularity based spectral clustering and mapping the Fiedler-carpet

Spectral clustering is discussed from many perspectives, by extending it...
research
04/30/2022

Understanding the Generalization Performance of Spectral Clustering Algorithms

The theoretical analysis of spectral clustering mainly focuses on consis...
research
12/16/2018

Connecting Spectral Clustering to Maximum Margins and Level Sets

We study the connections between spectral clustering and the problems of...
research
12/21/2015

Analysis of Vessel Connectivities in Retinal Images by Cortically Inspired Spectral Clustering

Retinal images provide early signs of diabetic retinopathy, glaucoma, an...
research
04/14/2011

Cluster Forests

With inspiration from Random Forests (RF) in the context of classificati...

Please sign up or login with your details

Forgot password? Click here to reset