Cutoff for exact recovery of Gaussian mixture models

Xiaohui Chen, Yun Yang

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.
BibTeX
@article{chen2021cutoff,
  author = {Xiaohui Chen and Yun Yang},
  title = {{Cutoff for exact recovery of Gaussian mixture models}},
  journal = {IEEE Trans. Information Theory},
  year = {2021},
  url = {https://openreview.net/forum?id=1PJs4bIZ06},
}

Loading related content...

Figure