Mirror Langevin diffusions: Convergence rates and Markov chain approximations

Benjamin Capdeville, Young-Heon Kim, Soumik Pal

Given a strongly convex function $u$, equip $R^d$ with a Riemannian metric given by the Hessian ${\nabla }^{2}u$. This is a so-called Hessian manifold. Given a probability density $\hat{I}¼$…