Learning mixtures of product distributions over discrete domains
FOCS '05 Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science
A rigorous analysis of population stratification with limited data
SODA '07 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
Multi-view clustering via canonical correlation analysis
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Group-Level Analysis and Visualization of Social Networks
Algorithmics of Large and Complex Networks
Application of a generalization of russo's formula to learning from multiple random oracles
Combinatorics, Probability and Computing
Separating populations with wide data: a spectral analysis
ISAAC'07 Proceedings of the 18th international conference on Algorithms and computation
Exploiting tag and word correlations for improved webpage clustering
SMUC '10 Proceedings of the 2nd international workshop on Search and mining user-generated contents
PAC learning axis-aligned mixtures of gaussians with no separation assumption
COLT'06 Proceedings of the 19th annual conference on Learning Theory
On spectral learning of mixtures of distributions
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Toward privacy in public databases
TCC'05 Proceedings of the Second international conference on Theory of Cryptography
A spectral algorithm for learning Hidden Markov Models
Journal of Computer and System Sciences
Leveraging Social Bookmarks from Partially Tagged Corpus for Improved Web Page Clustering
ACM Transactions on Intelligent Systems and Technology (TIST)
Learning mixtures of spherical gaussians: moment methods and spectral decompositions
Proceedings of the 4th conference on Innovations in Theoretical Computer Science
| Hi-index | 0.00 |
We show that a simple spectral algorithm for learning a mixture of k spherical Gaussians in Rn works remarkably well 驴 it succeeds in identifying the Gaussians assuming essentially the minimum possible separation between their centers that keeps them unique (solving an open problem of [1]). The sample complexity and running time are polynomial in both n and k. The algorithm also works for the more general problem of learning a mixture of "weakly isotropic" distributions (e.g. a mixture of uniform distributions on cubes).