The Annals of Statistics
- Ann. Statist.
- Volume 43, Number 1 (2015), 215-237.
Consistency of spectral clustering in stochastic block models
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.
Ann. Statist., Volume 43, Number 1 (2015), 215-237.
First available in Project Euclid: 9 December 2014
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Primary: 62F12: Asymptotic properties of estimators
Lei, Jing; Rinaldo, Alessandro. Consistency of spectral clustering in stochastic block models. Ann. Statist. 43 (2015), no. 1, 215--237. doi:10.1214/14-AOS1274. https://projecteuclid.org/euclid.aos/1418135620
- Supplementary material: Supplement to “Consistency of spectral clustering in sparse stochastic block models”. The supplementary file contains a proof of Theorem 5.2.