Optimality of Spectral Clustering for Gaussian Mixture Model

11/01/2019
by   Matthias Löffler, et al.
0

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. The spectral clustering algorithm is often used as a consistent initializer for more sophisticated clustering algorithms. However, in this paper, we show that spectral clustering is actually already optimal in the Gaussian Mixture Model, when the number of clusters of is fixed and consistent clustering is possible. Contrary to that spectral gap conditions are widely assumed in literature to analyze spectral clustering, these conditions are not needed in this paper to establish its optimality.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/12/2023

Spectral clustering algorithm for the allometric extension model

The spectral clustering algorithm is often used as a binary clustering m...
research
10/27/2022

Clustering High-dimensional Data via Feature Selection

High-dimensional clustering analysis is a challenging problem in statist...
research
04/29/2023

Spectral clustering in the Gaussian mixture block model

Gaussian mixture block models are distributions over graphs that strive ...
research
10/03/2019

On some spectral properties of stochastic similarity matrices for data clustering

Clustering in image analysis is a central technique that allows to class...
research
10/16/2019

A Notion of Harmonic Clustering in Simplicial Complexes

We outline a novel clustering scheme for simplicial complexes that produ...
research
09/01/2023

Consistency of Lloyd's Algorithm Under Perturbations

In the context of unsupervised learning, Lloyd's algorithm is one of the...
research
06/08/2017

Clustering with t-SNE, provably

t-distributed Stochastic Neighborhood Embedding (t-SNE), a clustering an...

Please sign up or login with your details

Forgot password? Click here to reset