Lower bounds on the smallest eigenvalue of a sample covariance matrix.

Pavel Yaskov (Steklov Mathematical Institute of RAS)

Abstract


We provide tight lower bounds on the smallest eigenvalue of a sample covariance matrix of a centred isotropic random vector under weak or no assumptions on its components.

Full Text: Download PDF | View PDF online (requires PDF plugin)

Pages: 1-10

Publication Date: December 6, 2014

DOI: 10.1214/ECP.v19-3807

References

  • KaĊĦin, B. S. The widths of certain finite-dimensional sets and classes of smooth functions. (Russian) Izv. Akad. Nauk SSSR Ser. Mat. 41 (1977), no. 2, 334--351. MR0481792
  • Kashin, B. S. On a special orthogonal decomposition of the space $L_2(0,1)$. Math. Notes 95 (2014), 570--572.
  • Krivine, Jean-Louis. On a theorem of Kashin. (French) Seminar on functional analysis, 1983/1984, 21--26, Publ. Math. Univ. Paris VII, 20, Univ. Paris VII, Paris, 1984. MR0825300
  • Koltchinskii, V.; Mendelson, S. Bounding the smallest singular value of a random matrix without concentration. arXiv:1312.3580
  • Oliveira, R.I. The lower tail of random quadratic forms, with applications to ordinary least squares and restricted eigenvalue properties. arXiv:1312.2903
  • Srivastava, Nikhil; Vershynin, Roman. Covariance estimation for distributions with $2+\varepsilon$ moments. Ann. Probab. 41 (2013), no. 5, 3081--3111. MR3127875
Bookmark and Share


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.