Cutoff for Exact Recovery of Gaussian Mixture Models
From MaRDI portal
Abstract: We determine the information-theoretic cutoff value on separation of cluster centers for exact recovery of cluster labels in a -component Gaussian mixture model with equal cluster sizes. Moreover, we show that a semidefinite programming (SDP) relaxation of the -means clustering method achieves such sharp threshold for exact recovery without assuming the symmetry of cluster centers.
Cited in
(12)- Optimality of spectral clustering in the Gaussian mixture model
- Sharp optimal recovery in the two component Gaussian mixture model
- An \({\ell_p}\) theory of PCA and spectral clustering
- The multidimensional truncated moment problem: Gaussian mixture reconstruction from derivatives of moments
- scientific article; zbMATH DE number 7307486 (Why is no real title available?)
- Criterion for signal extraction in underdetermined mixtures of bounded support
- Upper bound estimations of misclassification rate in the heteroscedastic clustering model with sub-Gaussian noises
- Optimal clustering by Lloyd's algorithm for low-rank mixture model
- Degree-Heterogeneous Latent Class Analysis for High-Dimensional Discrete Data
- Clustering a mixture of Gaussians with unknown covariance
- Optimal estimation of misclassification rate for two-class clustering with sub-Gaussian noises
- Nonnegative low-rank matrix recovery can have spurious local minima
This page was built for publication: Cutoff for Exact Recovery of Gaussian Mixture Models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5001786)
