A CLT in Stein's distance for generalized Wishart matrices and higher order tensors

02/25/2020
by   Dan Mikulincer, et al.
0

We study the convergence along the central limit theorem for sums of independent tensor powers, 1/√(d)∑_i=1^d X_i^⊗ p. We focus on the high-dimensional regime where X_i ∈R^n and n may scale with d. Our main result is a proposed threshold for convergence. Specifically, we show that, under some regularity assumption, if n^2p-1≫ d, 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 X_i^⊗ p.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/02/2020

Tensor optimal transport, distance between sets of measures and tensor scaling

We study the optimal transport problem for d>2 discrete measures. This i...
research
04/19/2022

An improved central limit theorem and fast convergence rates for entropic transportation costs

We prove a central limit theorem for the entropic transportation cost be...
research
03/09/2022

An entropic generalization of Caffarelli's contraction theorem via covariance inequalities

The optimal transport map between the standard Gaussian measure and an α...
research
05/28/2019

Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem

We prove several fundamental statistical bounds for entropic OT with the...
research
02/18/2022

Central limit theorem for full discretization of parabolic SPDE

In order to characterize the fluctuation between the ergodic limit and t...
research
12/07/2020

Uniform Central Limit Theorem for self normalized sums in high dimensions

In this article, we are interested in the normal approximation of the se...
research
05/30/2021

Re-evaluating Word Mover's Distance

The word mover's distance (WMD) is a fundamental technique for measuring...

Please sign up or login with your details

Forgot password? Click here to reset