The Product of Gaussian Matrices is Close to Gaussian

TL;DR

This paper demonstrates that the product of independent Gaussian matrices approximates a Gaussian matrix under certain size conditions, with the approximation improving as matrix dimensions grow large.

Contribution

It establishes conditions under which Gaussian matrix products are close to Gaussian matrices, providing both positive results and a converse for fixed number of matrices.

Findings

Matrix product approximates Gaussian distribution when dimensions are large.

Total variation distance decreases as matrix sizes increase.

A converse shows limitations when dimensions are too small.

Abstract

We study the distribution of the {\it matrix product} $G_1 G_2 \cdots G_r$ of $r$ independent Gaussian matrices of various sizes, where $G_i$ is $d_{i-1} \times d_i$, and we denote $p = d_0$, $q = d_r$, and require $d_1 = d_{r-1}$. Here the entries in each $G_i$ are standard normal random variables with mean $0$ and variance $1$. Such products arise in the study of wireless communication, dynamical systems, and quantum transport, among other places. We show that, provided each $d_i$, $i = 1, \ldots, r$, satisfies $d_i \geq C p \cdot q$, where $C \geq C_0$ for a constant $C_0 > 0$ depending on $r$, then the matrix product $G_1 G_2 \cdots G_r$ has variation distance at most $\delta$ to a $p \times q$ matrix $G$ of i.i.d.\ standard normal random variables with mean $0$ and variance $\prod_{i=1}^{r-1} d_i$. Here $\delta \rightarrow 0$ as $C \rightarrow \infty$. Moreover, we show a converse for constant $r$ that if $d_i < C' \max\{p,q\}^{1/2}\min\{p,q\}^{3/2}$ for some $i$, then this total variation distance is at least $\delta'$, for an absolute constant $\delta' > 0$ depending on $C'$ and $r$. This converse is best possible when $p=\Theta(q)$.