On Learning Mixtures of Well-Separated Gaussians

2017 IEEE 58TH ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS), pp. 85.0-96, 2017.

Cited by: 23|Bibtex|Views22|Links
EI
Keywords:
mixtures of Gaussiansunsupervised learningclusteringparameter estimationsample complexityMore(1+)

Abstract:

We consider the problem of efficiently learning mixtures of a large number of spherical Gaussians, when the components of the mixture are well separated. In the most basic form of this problem, we are given samples from a uniform mixture of k standard spherical Gaussians with means mu(1),..., mu(k) is an element of R-d, and the goal is to...More

Code:

Data:

Your rating :
0

 

Tags
Comments