Spectral Clustering via the Power Method -- Provably
Preprint
Abstract
Spectral clustering is one of the most important algorithms in data mining and machine intelligence; however, its computational complexity limits its application to truly large scale data analysis. The computational bottleneck in spectral clustering is computing a few of the top eigenvectors of the (normalized) Laplacian matrix corresponding to the graph representing the data to be clustered. One way to speed up the computation of these eigenvectors is to use the "power method" from the numerical linear algebra literature. Although the power method has been empirically used to speed up spectral clustering, the theory behind this approach, to the best of our knowledge, remains unexplored. This paper provides the \emph{first} such rigorous theoretical justification, arguing that a small number of power iterations suffices to obtain near-optimal partitionings using the approximate eigenvectors. Specifically, we prove that solving the $k$-means clustering problem on the approximate eigenvectors obtained via the power method gives an additive-error approximation to solving the $k$-means problem on the optimal eigenvectors.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Dimensionality Reduction for k-Means Clustering and Low Rank Approximation2015
- Faster SVD-truncated regularized least-squares2014
- Nearly Linear Time Algorithms for Preconditioning and Solving Symmetric, Diagonally Dominant Linear SystemsSIAM Journal on Matrix Analysis and Applications, 2014
- The effectiveness of lloyd-type methods for the k-means problemJournal of the ACM, 2012
- Fast approximate spectral clustering2009
- Approximate clustering in very large relational dataInternational Journal of Intelligent Systems, 2006