Efficient Sampling on Riemannian Manifolds via Langevin MCMC

arXiv:2402.10357v1 Announce Type: cross
Abstract: We study the task of efficiently sampling from a Gibbs distribution $d \pi^* = e^{-h} d {vol}_g$ over a Riemannian manifold $M$ via (geometric) Langevin MCMC; this algorithm involves computing exponential maps in random Gaussian directions and is efficiently implementable in practice. The key to our analysis of Langevin MCMC is a bound on the discretization error of the geometric Euler-Murayama scheme, assuming $\nabla h$ is Lipschitz and $M$ has bounded sectional curvature. Our error …

abstract algorithm analysis arxiv computing cs.lg distribution gibbs key manifold maps math.pr math.st mcmc practice random sampling stat.co stat.ml stat.th study the key type via