Mathematics – Probability
Scientific paper
2005-03-22
Annals of Applied Probability 2005, Vol. 15, No. 1A, 69-92
Mathematics
Probability
Published at http://dx.doi.org/10.1214/105051604000000512 in the Annals of Applied Probability (http://www.imstat.org/aap/) by
Scientific paper
10.1214/105051604000000512
Mixtures of Gaussian (or normal) distributions arise in a variety of application areas. Many heuristics have been proposed for the task of finding the component Gaussians given samples from the mixture, such as the EM algorithm, a local-search heuristic from Dempster, Laird and Rubin [J. Roy. Statist. Soc. Ser. B 39 (1977) 1-38]. These do not provably run in polynomial time. We present the first algorithm that provably learns the component Gaussians in time that is polynomial in the dimension. The Gaussians may have arbitrary shape, but they must satisfy a ``separation condition'' which places a lower bound on the distance between the centers of any two component Gaussians. The mathematical results at the heart of our proof are ``distance concentration'' results--proved using isoperimetric inequalities--which establish bounds on the probability distribution of the distance between a pair of points generated according to the mixture. We also formalize the more general problem of max-likelihood fit of a Gaussian mixture to unstructured data.
Arora Sanjeev
Kannan Ravi
No associations
LandOfFree
Learning mixtures of separated nonspherical Gaussians does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Learning mixtures of separated nonspherical Gaussians, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning mixtures of separated nonspherical Gaussians will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-684546