论文标题
精确恢复高斯混合模型的截止
Cutoff for exact recovery of Gaussian mixture models
论文作者
论文摘要
我们确定了群集中心分离的信息理论截止值，以精确恢复$ k $ - 组成的高斯混合模型，具有相等的群集大小。此外，我们表明，$ k $ -MEANS聚类方法的半决赛编程（SDP）放松达到了如此尖锐的阈值，以确切恢复，而无需假设集群中心的对称性。
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.
