Edge statistics of Dyson Brownian motion

Abstract

We consider the edge statistics of Dyson Brownian motion with deterministic initial data. Our main result states that if the initial data has a spectral edge with rough square root behavior down to a scale $\eta_* \geq N^{-2/3}$ and no outliers, then after times $t \gg \sqrt{ \eta_*}$, the statistics at the spectral edge agree with the GOE/GUE. In particular we obtain the optimal time to equilibrium at the edge $t = N^{\varepsilon} / N^{1/3}$ for sufficiently regular initial data. Our methods rely on eigenvalue rigidity results similar to those appearing in [Lee-Schnelli], the coupling idea of [Bourgade-Erd\H{o}s-Yau-Yin] and the energy estimate of [Bourgade-Erd\H{o}s-Yau].