English

Concentration inequalities for polynomials in $\alpha$-sub-exponential random variables

Probability 2021-04-26 v1

Abstract

In this work we derive multi-level concentration inequalities for polynomial functions in independent random variables with a α\alpha-sub-exponential tail decay. A particularly interesting case is given by quadratic forms f(X1,,Xn)=X,AXf(X_1, \ldots, X_n) = \langle X,A X \rangle, for which we prove Hanson-Wright-type inequalities with explicit dependence on various norms of the matrix AA. A consequence of these inequalities is a two-level concentration inequality for quadratic forms in α\alpha-sub-exponential random variables, such as quadratic Poisson chaos. We provide various applications of these inequalities. Among these are generalizations the results given by Rudelson-Vershynin from sub-Gaussian to α\alpha-sub-exponential random variables, i. e. concentration of the Euclidean norm of the linear image of a random vector, small ball probability estimates and concentration inequalities for the distance between a random vector and a fixed subspace. Moreover, we obtain concentration inequalities for the excess loss in a fixed design linear regression and the norm of a randomly projected random vector.

Keywords

Cite

@article{arxiv.1903.05964,
  title  = {Concentration inequalities for polynomials in $\alpha$-sub-exponential random variables},
  author = {Friedrich Götze and Holger Sambale and Arthur Sinulis},
  journal= {arXiv preprint arXiv:1903.05964},
  year   = {2021}
}
R2 v1 2026-06-23T08:08:01.662Z