arXiv cs.LG
· Papers
A Fourier analytique approach to Gaussian mixture learning
arXiv:2004.05813v3 Announce Type: replace-cross Abstract: Suppose that we are given independent, identically distributed random samples $x_1,cdots,x_n$ from a mixture at most $k$ many $d$-dimensional spherical Gaussian distributions $mu_1,cdots,mu_{k_0}$ of identical and known variance $sigma^2$ in each coordinate