RM+ML: 11. What Does a Large Random Covariance Matrix Look Like? — Marchenko–Pastur Law

The lecture notes for the course can be found at https://rolandspeicher.com/wp-content... concentration of eigenvalue distribution, classical statistics, modern statistics, Marchenko-Pastur distribution 0:00 Recap of Wishart Matrix Setting 5:07 Concentration of Eigenvalue Distribution 36:38 Marchenko-Pastur Law 49:06 Histogram Versus Moments Versus Resolvents The goal of this lecture series is to cover mathematical interesting aspects of neural networks, in particular, those related to random matrices. In this eleventh lecture we first consider the concentration of the eigenvalue distribution of Wishart matrices and then describe their asymptotic eigenvalue distribution via the Marchenko-Pastur law.