The Galactic halo is supposed to form from merging with nearby dwarf galaxies. In order probe different components of the halo, we have applied Gaussian Mixture Models method a selected sample metal poor stars [Fe/H] $< -0.7$ dex in APOGEE DR16 catalogue based on four-parameters, metallicity, [Mg/Fe] ratio and spatial velocity (\textit{$V_R$, $V_\phi$}). Nine groups are identified four (group 1...

We determine the information-theoretic cutoff value on separation of cluster centers for exact recovery labels in a K-component Gaussian mixture model with equal sizes. Moreover, we show that semidefinite programming (SDP) relaxation K-means clustering method achieves such sharp threshold without assuming symmetry centers.

In the traditional object recognition pipeline, descriptors are densely sampled over an image, pooled into a high dimensional non-linear representation and then passed to a classifier. In recent years, Fisher Vectors have proven empirically to be the leading representation for a large variety of applications. The Fisher Vector is typically taken as the gradients of the log-likelihood of descrip...