Home | Contents | Submissions, editors, etc. | Login | Search | EJP
 Electronic Communications in Probability > Vol. 14 (2009) > Paper 33 open journal systems 


Concentration of the spectral measure of large Wishart matrices with dependent entries

Adityanand Guntuboyina, Yale University
Hannes Leeb, Yale University


Abstract
We derive concentration inequalities for the spectral measure of large random matrices, allowing for certain forms of dependence. Our main focus is on empirical covariance (Wishart) matrices, but general symmetric random matrices are also considered.


Full text: PDF

Pages: 334-342

Published on: August 12, 2009


Bibliography
  1. Azuma, Kazuoki. Weighted sums of certain dependent random variables. Tôhoku Math. J. (2) 19 1967 357--367. MR0221571 (36 #4623)
  2. Bai, Zhidong; Zhou, Wang. Large sample covariance matrices without independence structures in columns. Statist. Sinica 18 (2008), no. 2, 425--442. MR2411613 (2009d:60075)
  3. Bai, Z. D. Methodologies in spectral analysis of large-dimensional random matrices, a review.With comments by G. J. Rodgers and Jack W. Silverstein; and a rejoinder by the author. Statist. Sinica 9 (1999), no. 3, 611--677. MR1711663 (2000e:60044)
  4. Boucheron, Stéphane; Lugosi, Gábor; Massart, Pascal. Concentration inequalities using the entropy method. Ann. Probab. 31 (2003), no. 3, 1583--1614. MR1989444 (2004i:60023)
  5. Boutet de Monvel, A.; Khorunzhy, A. Limit theorems for random matrices. Markov Process. Related Fields 4 (1998), no. 2, 175--197. MR1641617 (99k:60100)
  6. Chernoff, Herman. A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations. Ann. Math. Statistics 23, (1952). 493--507. MR0057518 (15,241c)
  7. Götze, F.; Tikhomirov, A. Limit theorems for spectra of positive random matrices under dependence. Zap. Nauchn. Sem. S.-Peterburg. Otdel. Mat. Inst. Steklov. (POMI) 311 (2004), Veroyatn. i Stat. 7, 92--123, 299; translation in J. Math. Sci. (N. Y.) 133 (2006), no. 3, 1257--1276 MR2092202 (2005m:15067)
  8. Guionnet, Alice. Large deviations and stochastic calculus for large random matrices. Probab. Surv. 1 (2004), 72--172 (electronic). MR2095566 (2006e:60037)
  9. Guionnet, A.; Zeitouni, O. Concentration of the spectral measure for large matrices. Electron. Comm. Probab. 5 (2000), 119--136 (electronic). MR1781846 (2001k:15035)
  10. Hoeffding, Wassily. Probability inequalities for sums of bounded random variables. J. Amer. Statist. Assoc. 58 1963 13--30. MR0144363 (26 #1908)
  11. Houdré, Christian; Xu, Hua. Concentration of the spectral measure for large random matrices with stable entries. Electron. J. Probab. 13 (2008), no. 5, 107--134. MR2375601 (2009a:60014)
  12. Lang, Serge. Real and functional analysis.Third edition.Graduate Texts in Mathematics, 142. Springer-Verlag, New York, 1993. xiv+580 pp. ISBN: 0-387-94001-4 MR1216137 (94b:00005)
  13. Lieb, Elliott H.; Pedersen, Gert K. Convex multivariable trace functions.Dedicated to Professor Huzihiro Araki on the occasion of his 70th birthday. Rev. Math. Phys. 14 (2002), no. 7-8, 631--648. MR1932659 (2003j:46080)
  14. Maurey, B. Some deviation inequalities. Geom. Funct. Anal. 1 (1991), no. 2, 188--197. MR1097258 (92g:60024)
  15. McDiarmid, Colin. On the method of bounded differences. Surveys in combinatorics, 1989 (Norwich, 1989), 148--188, London Math. Soc. Lecture Note Ser., 141, Cambridge Univ. Press, Cambridge, 1989. MR1036755 (91e:05077)
  16. Mendelson, Shahar; Pajor, Alain. On singular values of matrices with independent rows. Bernoulli 12 (2006), no. 5, 761--773. MR2265341 (2008a:60160)
  17. Talagrand, Michel. A new look at independence. Ann. Probab. 24 (1996), no. 1, 1--34. MR1387624 (97d:60028)
  18. Walsh, J. L. A Closed Set of Normal Orthogonal Functions. Amer. J. Math. 45 (1923), no. 1, 5--24. MR1506485
















Research
Support Tool
Capture Cite
View Metadata
Printer Friendly
Context
Author Address
Action
Email Author
Email Others


Home | Contents | Submissions, editors, etc. | Login | Search | EJP

Electronic Communications in Probability. ISSN: 1083-589X