The spectral method for general mixture models

SIAM Journal on Computing

Volumn 38, Issue 3, 2008, Pages 1141-1156

  Ravindran, Kannan ^a   Hadi, Salmasian ^b   Santosh, Vempala ^c,d  

^a Yale University   (United States)

^b UNIVERSITY OF WINDSOR   (Canada)

^c Georgia Institute of Technology   (United States)

^d MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Logconcave distributions; Mixture models; Principal component analysis; Singular value decomposition

Indexed keywords

ARBITRARY MIXTURES; GAUSSIANS; GENERAL MIXTURE MODELS; LOGCONCAVE DISTRIBUTIONS; MIXTURE MODELS; MIXTURE OF DISTRIBUTIONS; NUMBER OF COMPONENTS; SPECTRAL METHODS; SPECTRAL PROJECTIONS;

IMAGE SEGMENTATION; ISOMERS; MIXTURES; PRINCIPAL COMPONENT ANALYSIS; SINGULAR VALUE DECOMPOSITION;

LEARNING ALGORITHMS;

EID: 55249121402     PISSN: 00975397     EISSN: None     Source Type: Journal    
DOI: 10.1137/S0097539704445925     Document Type: Article

References (21)

1. D. ACHLIOPTAS AND F. MCSHERRY, On spectral learning of mixtures of distributions, in Learning Theory, Springer, Berlin, 2005, pp. 458-469.
2. S. ARORA AND R. KANNAN, Learning mixtures of arbitrary Gaussians, Ann. Appl. Probab., 15 (2005), pp. 69-92.
3. S. DASGUPTA, Learning mixtures of Gaussians, in Proceedings of the 40th Annual IEEE Symposium on Foundations of Computer Science, 1999, pp. 634-644.
4. S. DASGUPTA AND L. SCHULMAN, A two-round variant of EM for Gaussian mixtures, in Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann, San Francisco, 2000, pp. 152-159.
5. A. P. DEMPSTER, N. M. LAIRD, AND D. B. RUBIN, Maximum likelihood from incomplete data via the EM algorithm. With discussion, J. Roy. Statist. Soc. Ser. B. 39 (1977), pp. 1-38.
6. A. DINGHAS, Über eine Klasse superadditiver Mengenfunktionale von Brunn-Minkowski-Lusternik-schem Typus, Math. Z., 68 (1957), pp. 111-125.
7. A. A. GIANNOPOULOS AND V. D. MILMAN, Concentration property on probability spaces, Adv. Math., 156 (2000), pp. 77-106.
8. G. GOLUB AND C. VAN LOAN, Matrix: Computations, The Johns Hopkins University Press, Baltimore, MD, 1989.
9. R. KANNAN, H. SALMASIAN, AND S. VEMPALA, The spectral method for general mixture models, in Learning Theory, Lecture Notes in Comput. Sci. 3559, Springer, Berlin, 2005, pp. 444-457.
10. M. KEARNS AND U. VAZIRANI An Introduction to Computational Learning Theory, MIT Press, Cambridge, MA, 1994.
11. L. LEINDLER, On a certain converse of Hölder's Inequality II, Acta Sci. Math. (Szeged), 33 (1972), pp. 217-223.
12. B. LINDSAY, Mixture Models: Theory, Geometry and Applications, American Statistical Association, Alexandria, VA, 1995.
13. L. LOVÁSZ AND S. VEMPALA, The geometry of logconcave functions and sampling algorithms, Random Structures Algorithms, 30 (2007), pp. 307-358.
14. R. MOTWANI AND P. RAGHAVAN, Randomized Algorithms, Cambridge University Press, Cambridge, UK, 1995.
15. A. PRÉKOPA, Logarithmic concave measures and functions, Acta Sci. Math. (Szeged), 34 (1973), pp. 335-343.
16. M. RUDELSON, Random vectors in the isotropic position, J. Funct. Anal., 164 (1999), pp. 60-72.
17. D. M. TITTERINGTON, A. F. M. SMITH, AND U. E. MAKOV, Statistical Analysis of Finite Mixture Distributions, Wiley, Chichester, UK, 1985.
18. S. VEMPALA, On the Spectral Method for Mixture Models, IMA Workshop on Data Analysis and Optimization, 2003; http://www.ima.umn.edu/ talks/workshops/5-6-9.2003/vempala/vempala.html.
19. S. VEMPALA AND G. WANG, A spectral algorithm for learning mixtures of distributions, J. Comput. System Sci., 68 (2004), pp. 841-860.
20. S. VEMPALA AND G. WANG, The benefit of spectral projection for document clustering, in Proceedings of the 3rd Annual Workshop on Clustering High Dimensional Data and its Applications, SIAM International Conference on Data Mining, 2005.
21. C. F. J. WU, On the convergence properties of the EM algorithm, Ann. Statist., 11 (1983), pp. 95-103.