Name
Abstract | ||
|---|---|---|
We determine the information-theoretic cutoff value on separation of cluster centers for exact recovery of cluster labels in a K-component Gaussian mixture model with equal cluster sizes. Moreover, we show that a semidefinite programming (SDP) relaxation of the K-means clustering method achieves such sharp threshold for exact recovery without assuming the symmetry of cluster centers. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/TIT.2021.3063155 | IEEE Transactions on Information Theory |
Keywords | DocType | Volume |
Clustering algorithms,Gaussian mixture model,Partitioning algorithms,Maximum likelihood estimation,Mixture models,Machine learning algorithms,Clustering methods | Journal | 67 |
Issue | ISSN | Citations |
6 | 0018-9448 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chen Xiaohui | 1 | 0 | 0.34 |
| Yang Yun | 2 | 0 | 0.34 |