Heat Kernel Empirical Laws on $\mathbb{U}_N$ and $\mathbb{GL}_N$

Abstract

This paper studies the empirical measures of eigenvalues and singular values for random matrices drawn from the heat kernel measures on the unitary groups $\mathbb{U}_N$ and the general linear groups $\mathbb{GL}_N$, for $N\in\mathbb{N}$. It establishes the strongest known convergence results for the empirical eigenvalues in the $\mathbb{U}_N$ case, and the first known almost sure convergence results for the eigenvalues and singular values in the $\mathbb{GL}_N$ case. The limit noncommutative distribution associated to the heat kernel measure on $\mathbb{GL}_N$ is identified as the projection of a flow on an infinite-dimensional polynomial space. These results are then strengthened from variance estimates to $L^p$ estimates for even integers $p$.