Electronic Journal of Statistics
- Electron. J. Statist.
- Volume 10, Number 1 (2016), 1393-1454.
Kernel spectral clustering of large dimensional data
This article proposes a first analysis of kernel spectral clustering methods in the regime where the dimension $p$ of the data vectors to be clustered and their number $n$ grow large at the same rate. We demonstrate, under a $k$-class Gaussian mixture model, that the normalized Laplacian matrix associated with the kernel matrix asymptotically behaves similar to a so-called spiked random matrix. Some of the isolated eigenvalue-eigenvector pairs in this model are shown to carry the clustering information upon a separability condition classical in spiked matrix models. We evaluate precisely the position of these eigenvalues and the content of the eigenvectors, which unveil important (sometimes quite disruptive) aspects of kernel spectral clustering both from a theoretical and practical standpoints. Our results are then compared to the actual clustering performance of images from the MNIST database, thereby revealing an important match between theory and practice.
Electron. J. Statist. Volume 10, Number 1 (2016), 1393-1454.
Received: November 2015
First available in Project Euclid: 31 May 2016
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Primary: 62H30: Classification and discrimination; cluster analysis [See also 68T10, 91C20] 60B20: Random matrices (probabilistic aspects; for algebraic aspects see 15B52)
Secondary: 15B52: Random matrices
Couillet, Romain; Benaych-Georges, Florent. Kernel spectral clustering of large dimensional data. Electron. J. Statist. 10 (2016), no. 1, 1393--1454. doi:10.1214/16-EJS1144. https://projecteuclid.org/euclid.ejs/1464710237