Asymptotic bias of inexact Markov Chain Monte Carlo methods in high dimension

08/02/2021
by   Alain Durmus, et al.
0

This paper establishes non-asymptotic bounds on Wasserstein distances between the invariant probability measures of inexact MCMC methods and their target distribution. In particular, the results apply to the unadjusted Langevin algorithm and to unadjusted Hamiltonian Monte Carlo, but also to methods relying on other discretization schemes. Our focus is on understanding the precise dependence of the accuracy on both the dimension and the discretization step size. We show that the dimension dependence relies on some key quantities. As a consequence, the same dependence on the step size and the dimension as in the product case can be recovered for several important classes of models. On the other hand, for more general models, the dimension dependence of the asymptotic bias may be worse than in the product case even if the exact dynamics has dimension-free mixing properties.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2021

Mixing Time Guarantees for Unadjusted Hamiltonian Monte Carlo

We provide quantitative upper bounds on the total variation mixing time ...
research
11/06/2020

On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method

The randomized midpoint method, proposed by [SL19], has emerged as an op...
research
01/02/2015

(Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics

Applying standard Markov chain Monte Carlo (MCMC) algorithms to large da...
research
02/13/2020

Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization

We provide a nonasymptotic analysis of the convergence of the stochastic...
research
01/15/2020

Newtonian Monte Carlo: single-site MCMC meets second-order gradient methods

Single-site Markov Chain Monte Carlo (MCMC) is a variant of MCMC in whic...
research
01/06/2022

On the geometric convergence for MALA under verifiable conditions

While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and...
research
06/19/2020

Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis

Recently, the task of image generation has attracted much attention. In ...

Please sign up or login with your details

Forgot password? Click here to reset