A spectral algorithm for learning mixture models

Journal of Computer and System Sciences

Volumn 68, Issue 4, 2004, Pages 841-860

  Vempala, Santosh ^a,b   Wang, Grant ^b  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; POLYNOMIALS; PROBABILITY; PROBLEM SOLVING; SAMPLING; SPECTRUM ANALYSIS;

MIXTURE MODELS; RUNNING TIME; SAMPLE COMPLEXITY; SPECTRAL ALGORITHMS;

LEARNING SYSTEMS;

EID: 3042606899     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jcss.2003.11.008     Document Type: Conference Paper

References (14)

1. S. Arora, R. Kannan, Learning mixtures of arbitrary gaussians, in: Proceedings of the 33rd ACM STOC, Crete, Greece, 2001.
2. Y. Azar, A. Fiat, A. Karlin, F. McSherry, and J. Saia, Spectral analysis of data, in: Proceedings of the 33rd ACM STOC, Crete, Greece, 2001.
3. S. DasGupta, Learning mixtures of gaussians, in: Proceedings of the 40th IEEE FOCS, New York, NY, 1999.
4. S. DasGupta, L. Schulman, A two-round variant of em for gaussian mixtures, in: Proceedings of the 16th Conference in Uncertianty in Artificial Intelligence, Stanford, CA, 2000.
5. Dempster A.P., Laird N.M., Rubin D.B. Maximum likelihood from incomplete data via the em algorithm. J. Roy. Statist. Soc. Ser. B. 39:1977;1-38.
6. P. Drineas, R. Kannan, A. Frieze, S. Vempala, V. Vinay, Clustering in large graphs and matrices, in: Proceedings of the 10th SIAM SODA, Baltimore, MD, 1999.
7. Eaton M.L. Multivariate Statistics. 1983;Wiley, New York.
8. A. Frieze, R. Kannan, S. Vempala, Fast monte-carlo algorithms for finding low-rank approximations, in: Proceedings of the 39th IEEE FOCS, Palo Alto, CA, 1998.
9. Kannan R., Lovász L., Simonovits M. Isoperimetric problems for convex bodies and a localization lemma. Discrete Comput. Geom. 13:1995;541-559.
10. Lindsay B. Mixture models: Theory, Geometry and Applications. 1995;American Statistical Association, Alexandria, VA.
11. L. Lovász, S. Vempala, Logconcave functions: geometry and efficient sampling algorithms, in: Proceedings of the 44th IEEE FOCS, Boston, MA, 2003, to appear.
12. Papadimitriou C., Raghavan P., Tamaki H., Vempala S. Latent semantic indexing. a probabilistic analysis J. Comput. System Sci. 61:2000;217-235.
13. Stewart G. Error and perturbation bounds for subspaces associated with certain eigenvalue problems. SIAM Rev. 15(4):1973;727-764.
14. Titterington D.M., Smith A.F.M., Makov U.E. Statistical Analysis of Finite Mixture Distributions. 1985;Wiley, New York.