DeepAI AI Chat
Log In Sign Up

Higher Order Langevin Monte Carlo Algorithm

by   Sotirios Sabanis, et al.

A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and Wasserstein distance is presented in the context of sampling from a target distribution π under the assumption that its density on R^d is known up to a normalizing constant. Crucially, the Langevin SDE associated with the target distribution π is assumed to have a locally Lipschitz drift coefficient such that its second derivative is locally Hölder continuous with exponent β∈ (0,1]. In addition, non-asymptotic bounds are obtained for the convergence to stationarity of the new sampling method with convergence rate 1+ β/2 in Wasserstein distance, while it is shown that the rate is 1 in total variation. The bounds between the invariant measure of the LMC algorithm and π are also given.


page 1

page 2

page 3

page 4


Guarantees in Wasserstein Distance for the Langevin Monte Carlo Algorithm

We study the problem of sampling from a distribution using the Langevin...

Unajusted Langevin algorithm with multiplicative noise: Total variation and Wasserstein bounds

In this paper, we focus on non-asymptotic bounds related to the Euler sc...

Stability of doubly-intractable distributions

Doubly-intractable distributions appear naturally as posterior distribut...

High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm

We consider in this paper the problem of sampling a high-dimensional pro...

Sensitivity of Uncertainty Propagation for the Elliptic Diffusion Equation

For elliptic diffusion equations with random coefficient and source term...

Wasserstein-based methods for convergence complexity analysis of MCMC with application to Albert and Chib's algorithm

Over the last 25 years, techniques based on drift and minorization (d&m)...

High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion

The efficiency of a markov sampler based on the underdamped Langevin dif...