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

Abstract

The randomized midpoint method, proposed by [SL19], has emerged as an optimal discretization procedure for simulating the continuous time Langevin diffusions. Focusing on the case of strong-convex and smooth potentials, in this paper, we analyze several probabilistic properties of the randomized midpoint discretization method for both overdamped and underdamped Langevin diffusions. We first characterize the stationary distribution of the discrete chain obtained with constant step-size discretization and show that it is biased away from the target distribution. Notably, the step-size needs to go to zero to obtain asymptotic unbiasedness. Next, we establish the asymptotic normality for numerical integration using the randomized midpoint method and highlight the relative advantages and disadvantages over other discretizations. Our results collectively provide several insights into the behavior of the randomized midpoint discretization method, including obtaining confidence intervals for numerical integrations.

arXiv commentCorrected minor typos

References in corpus (14)

• Stochastic Gradient Hamiltonian Monte Carlo
• Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
• On the Geometric Ergodicity of Hamiltonian Monte Carlo
• Underdamped Langevin MCMC: A non-asymptotic analysis
• Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
• Convergence of Langevin MCMC in KL-divergence
• Is There an Analog of Nesterov Acceleration for MCMC?
• Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
• Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
• The Randomized Midpoint Method for Log-Concave Sampling
• Complexity of randomized algorithms for underdamped Langevin dynamics
• On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
• Higher Order Langevin Monte Carlo Algorithm
• On Thompson Sampling with Langevin Algorithms

Cited by in corpus (5)

• The shifted ODE method for underdamped Langevin MCMC
• Random Coordinate Underdamped Langevin Monte Carlo
• Convergence of Langevin Monte Carlo in Chi-Squared and Renyi Divergence
• Unadjusted Hamiltonian MCMC with Stratified Monte Carlo Time Integration
• Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited