Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Learning mixtures of arbitrary gaussians [Extended Abstract] #

Summary: Learning mixtures of arbitrary gaussians
[Extended Abstract] #
Sanjeev Arora +
Dept of Computer Science
Princeton University
Ravi Kannan #
Dept of Computer Science
Yale University
Mixtures of gaussian (or normal) distributions arise in a va­
riety of application areas. Many techniques have been pro­
posed 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 (1977).
However, such heuristics are known to require time expo­
nential in the dimension (i.e., number of variables) in the
worst case, even when the number of components is 2.
This paper presents the first algorithm that provably learns
the component gaussians in time that is polynomial in the
dimension. The gaussians may have arbitrary shape pro­


Source: Arora, Sanjeev - Department of Computer Science, Princeton University


Collections: Computer Technologies and Information Sciences