65
85
v1v2 (latest)

High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm

Abstract

We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes, and we develop a specific method that combines splitting with more accurate integration. For a broad class of dd-dimensional distributions arising from generalized linear models, we prove that the resulting third-order algorithm produces samples from a distribution that is at most ε>0\varepsilon > 0 in Wasserstein distance from the target distribution in O(d1/4ε1/2)O\left(\frac{d^{1/4}}{ \varepsilon^{1/2}} \right) steps. This result requires only Lipschitz conditions on the gradient. For general strongly convex potentials with α\alpha-th order smoothness, we prove that the mixing time scales as O(d1/4ε1/2+d1/2ε1/(α1))O \left(\frac{d^{1/4}}{\varepsilon^{1/2}} + \frac{d^{1/2}}{\varepsilon^{1/(\alpha - 1)}} \right).

View on arXiv
Comments on this paper