A CLT in Stein's distance for generalized Wishart matrices and higher order tensors
Probability
2020-11-05 v2 Statistics Theory
Statistics Theory
Abstract
We study the central limit theorem for sums of independent tensor powers, . We focus on the high-dimensional regime where and may scale with . Our main result is a proposed threshold for convergence. Specifically, we show that, under some regularity assumption, if , then the normalized sum converges to a Gaussian. The results apply, among others, to symmetric uniform log-concave measures and to product measures. This generalizes several results found in the literature. Our main technique is a novel application of optimal transport to Stein's method which accounts for the low dimensional structure which is inherent in .
Keywords
Cite
@article{arxiv.2002.10846,
title = {A CLT in Stein's distance for generalized Wishart matrices and higher order tensors},
author = {Dan Mikulincer},
journal= {arXiv preprint arXiv:2002.10846},
year = {2020}
}
Comments
22 pages. Added a section about non-homogenous sums and correlated Wishart matrices