no code implementations • 8 Sep 2020 • Fengshuo Zhang, Chao GAO
We study the convergence rates of empirical Bayes posterior distributions for nonparametric and high-dimensional inference.
no code implementations • 7 Dec 2017 • Fengshuo Zhang, Chao GAO
For a class of priors that admit the structure of a mixture of product measures, we propose a novel prior mass condition, under which the variational approximation error of the mean-field class is dominated by convergence rate of the true posterior.