Gaussian random field approximation via Stein's method with applications to wide random neural networks

no code implementations • 28 Jun 2023 • Krishnakumar Balasubramanian, Larry Goldstein, Nathan Ross, Adil Salim

Specializing our general result, we obtain the first bounds on the Gaussian random field approximation of wide random neural networks of any depth and Lipschitz activation functions at the random field level.