paper

Bounds on tail probabilities for quadratic forms in dependent sub-gaussian random variables

arXiv:1809.08569 · doi:10.1016/j.spl.2020.108898

Abstract

We show bounds on tail probabilities for quadratic forms in sub-gaussian non-necessarily independent random variables. Our main tool will be estimates of the Luxemburg norms of such forms. This will allow us to formulate the above-mentioned bounds. As an example we give estimates of the excess loss in fixed design linear regression in dependent observations.

11 pages

Bounds on tail probabilities for quadratic forms in dependent sub-gaussian random variables · wovepaper