Electronic Communications in Probability

A tail inequality for quadratic forms of subgaussian random vectors

Daniel Hsu, Sham Kakade, and Tong Zhang

Full-text: Open access

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.

Article information

Source
Electron. Commun. Probab. Volume 17 (2012), paper no. 52, 6 pp.

Dates
Accepted: 2 November 2012
First available in Project Euclid: 7 June 2016

Permanent link to this document
https://projecteuclid.org/euclid.ecp/1465263185

Digital Object Identifier
doi:10.1214/ECP.v17-2079

Mathematical Reviews number (MathSciNet)
MR2994877

Zentralblatt MATH identifier
1309.60017

Subjects
Primary: 60F10: Large deviations

Keywords
Tail inequality quadratic form subgaussian random vectors subgaussian chaos

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

Citation

Hsu, Daniel; Kakade, Sham; Zhang, Tong. A tail inequality for quadratic forms of subgaussian random vectors. Electron. Commun. Probab. 17 (2012), paper no. 52, 6 pp. doi:10.1214/ECP.v17-2079. https://projecteuclid.org/euclid.ecp/1465263185


Export citation

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.
  • Laurent, B.; Massart, P. Adaptive estimation of a quadratic functional by model selection. Ann. Statist. 28 (2000), no. 5, 1302–1338.
  • 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