Optimality of Spectral Clustering in the Gaussian Mixture Model
Statistics Theory
2020-08-07 v2 Machine Learning
Spectral Theory
Statistics Theory
Abstract
Spectral clustering is one of the most popular algorithms to group high dimensional data. It is easy to implement and computationally efficient. Despite its popularity and successful applications, its theoretical properties have not been fully understood. In this paper, we show that spectral clustering is minimax optimal in the Gaussian Mixture Model with isotropic covariance matrix, when the number of clusters is fixed and the signal-to-noise ratio is large enough. Spectral gap conditions are widely assumed in the literature to analyze spectral clustering. On the contrary, these conditions are not needed to establish optimality of spectral clustering in this paper.
Keywords
Cite
@article{arxiv.1911.00538,
title = {Optimality of Spectral Clustering in the Gaussian Mixture Model},
author = {Matthias Löffler and Anderson Y. Zhang and Harrison H. Zhou},
journal= {arXiv preprint arXiv:1911.00538},
year = {2020}
}