Year: 2014
Type: article
Abstract: We analyze the performance of spectral clustering for community extraction in stochastic block models. We show that, under mild conditions, spectral clustering applied to the adjacency matrix of the network can consistently recover hidden communities even when the order of the maximum expected degree is as small as $\log n$, with $n$ the number of nodes. This result applies to some popular polynomial time spectral clustering algorithms and is further extended to degree corrected stochastic block models using a spherical $k$-median spectral clustering method. A key component of our analysis is a combinatorial bound on the spectrum of binary random matrices, which is sharper than the conventional matrix Bernstein inequality and may be of independent interest.
Source: The Annals of Statistics
DOI: 10.1214/14-aos1274
Authors: Jing Lei, Alessandro Rinaldo
Institution: Carnegie Mellon University
Language: English
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: bronze
Awards: G1523888516, G6071252945, G6671297155, CAREER: STATISTICAL INFERENCE FOR TOPOLOGICAL AND GEOMETRIC DATA ANALYSIS, G7830320759, CDI-Type II: Collaborative Research: Integrating Statistical and Computational Approaches to Privacy, G9000027892, Spectral and principal components analysis in sparse, high-dimensional data
OpenAlex ID: W2051638434
