SIAM Journal on Computing · 2008 · 71 citations · 13 references
ComputingComputer ScienceMachine LearningStatistical LearningStatistical ModelingGenerative ModelingUnsupervised LearningFinite Mixture ModelsGaussian Mixture ModelsMixture DistributionsMixture ModelMixture Model AnalysisMixture Theory
We present an algorithm for learning a mixture of distributions based on spectral projection. We prove a general property of spectral projection for arbitrary mixtures and show that the resulting algorithm is efficient when the components of the mixture are logconcave distributions in $\Re^n$ whose means are separated. The separation required grows with k, the number of components, and $\log n$. This is the first result demonstrating the benefit of spectral projection for general Gaussians and widens the scope of this method. It improves substantially on previous results, which focus either on the special case of spherical Gaussians or require a separation that has a considerably larger dependence on n.
13
On the Convergence Properties of the EM Algorithm
Changbao Wu · The Annals of Statistics · 1983 · 3.3K citations · Full text
Learning mixtures of Gaussians
Sanjoy Dasgupta · 2003 · 624 citations
Random Vectors in the Isotropic Position
Mark Rudelson · Journal of Functional Analysis · 1999 · 398 citations