Sparse Hanson-Wright inequalities for subgaussian quadratic forms
Abstract
In this paper, we provide a proof for the Hanson-Wright inequalities for sparsified quadratic forms in subgaussian random variables. This provides useful concentration inequalities for sparse subgaussian random vectors in two ways. Let be a random vector with independent subgaussian components, and be independent Bernoulli random variables. We prove the large deviation bound for a sparse quadratic form of , where is an matrix, and random vector denotes the Hadamard product of an isotropic subgaussian random vector and a random vector such that , where are independent Bernoulli random variables. The second type of sparsity in a quadratic form comes from the setting where we randomly sample the elements of an anisotropic subgaussian vector where is an symmetric matrix; we study the large deviation bound on the -norm of from its expected value, where for a given vector , denotes the diagonal matrix whose main diagonal entries are the entries of . This form arises naturally from the context of covariance estimation.
Cite
@article{arxiv.1510.05517,
title = {Sparse Hanson-Wright inequalities for subgaussian quadratic forms},
author = {Shuheng Zhou},
journal= {arXiv preprint arXiv:1510.05517},
year = {2017}
}
Comments
29 pages; added full proof of Theorem 1.2 using moment generating functions, which had appeared in TR 539, October 2015