A tail inequality for quadratic forms of subgaussian random vectors

Daniel Hsu (Microsoft Research New England)
Sham M. Kakade (Microsoft Research New England)
Tong Zhang (Rutgers University)

Abstract


This article proves an exponential probability tail inequality for positive semidefinite quadratic forms in a subgaussian random vector. The bound is analogous to one that holds when the vector has independent Gaussian entries.


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

Pages: 1-6

Publication Date: November 2, 2012

DOI: 10.1214/ECP.v17-2079

References

  • Hanson, D. L.; Wright, F. T. A bound on tail probabilities for quadratic forms in independent random variables. Ann. Math. Statist. 42 1971 1079--1083. MR0279864
  • Laurent, B.; Massart, P. Adaptive estimation of a quadratic functional by model selection. Ann. Statist. 28 (2000), no. 5, 1302--1338. MR1805785
  • Pisier, Gilles. The volume of convex bodies and Banach space geometry. Cambridge Tracts in Mathematics, 94. Cambridge University Press, Cambridge, 1989. xvi+250 pp. ISBN: 0-521-36465-5; 0-521-66635-X MR1036275
Bookmark and Share


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