Corpus ID: 207780368

Optimality of Spectral Clustering for Gaussian Mixture Model

@article{Lffler2019OptimalityOS,
  title={Optimality of Spectral Clustering for Gaussian Mixture Model},
  author={Matthias L{\"o}ffler and A. Zhang and H. Zhou},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.00538}
}
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… Expand
14 Citations
Spectral Methods for Data Science: A Statistical Perspective
  • 5
  • Highly Influenced
  • PDF
An $\ell_p$ theory of PCA and spectral clustering.
  • 1
  • Highly Influenced
  • PDF
A Robust Spectral Clustering Algorithm for Sub-Gaussian Mixture Models with Outliers
  • 4
  • Highly Influenced
  • PDF
Optimal Clustering in Anisotropic Gaussian Mixture Models
  • PDF
Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates
  • 1
  • PDF
Computationally efficient sparse clustering
  • 2
  • PDF
Efficient Clustering for Stretched Mixtures: Landscape and Optimality
  • 3
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 95 REFERENCES
Statistical analysis of finite mixture distributions
  • 3,354
  • Highly Influential
Consistency of spectral clustering in stochastic block models
  • 346
  • Highly Influential
  • PDF
FAST COMMUNITY DETECTION BY SCORE
  • J. Jin
  • Mathematics, Computer Science
  • 2015
  • 175
  • Highly Influential
  • PDF
Spectral clustering and the high-dimensional stochastic blockmodel
  • 648
  • Highly Influential
  • PDF
Statistical and Computational Guarantees of Lloyd's Algorithm and its Variants
  • Yu Lu, H. Zhou
  • Mathematics, Computer Science
  • ArXiv
  • 2016
  • 60
  • PDF
An 𝓁p theory of PCA and spectral clustering
  • 4
Cutoff for exact recovery of Gaussian mixture models
  • 4
  • PDF
Cuto↵ for exact recovery of gaussian mixture models
  • arXiv preprint,
  • 2020
ENTRYWISE EIGENVECTOR ANALYSIS OF RANDOM MATRICES WITH LOW EXPECTED RANK.
  • 114
  • PDF
Eigen selection in spectral clustering: a theory guided practice
  • 2
  • PDF
...
1
2
3
4
5
...