Metropolis Adjusted Langevin Trajectories: a robust alternative to Hamiltonian Monte Carlo

02/26/2022
by   Lionel Riou-Durand, et al.
0

Hamiltonian Monte Carlo (HMC) is a widely used sampler, known for its efficiency on high dimensional distributions. Yet HMC remains quite sensitive to the choice of integration time. Randomizing the length of Hamiltonian trajectories (RHMC) has been suggested to smooth the Auto-Correlation Functions (ACF), ensuring robustness of tuning. We present the Langevin diffusion as an alternative to control these ACFs by inducing randomness in Hamiltonian trajectories through a continuous refreshment of the velocities. We connect and compare the two processes in terms of quantitative mixing rates for the 2-Wasserstein and 𝕃_2 distances. The Langevin diffusion is presented as a limit of RHMC achieving the fastest mixing rate for strongly log-concave targets. We introduce a robust alternative to HMC built upon these dynamics, named Metropolis Adjusted Langevin Trajectories (MALT). Studying the scaling limit of MALT, we obtain optimal tuning guidelines similar to HMC, and recover the same scaling with respect to the dimension without additional assumptions. We illustrate numerically the efficiency of MALT compared to HMC and RHMC.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/23/2017

Rapid Mixing of Hamiltonian Monte Carlo on Strongly Log-Concave Distributions

We obtain several quantitative bounds on the mixing properties of the Ha...
research
10/21/2022

Adaptive Tuning for Metropolis Adjusted Langevin Trajectories

Hamiltonian Monte Carlo (HMC) is a widely used sampler for continuous pr...
research
12/23/2020

Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm

Conventional wisdom in the sampling literature, backed by a popular diff...
research
09/15/2022

On the Dissipation of Ideal Hamiltonian Monte Carlo Sampler

We report on what seems to be an intriguing connection between variable ...
research
12/15/2021

The Apogee to Apogee Path Sampler

Amongst Markov chain Monte Carlo algorithms, Hamiltonian Monte Carlo (HM...
research
11/17/2020

Convergence of Preconditioned Hamiltonian Monte Carlo on Hilbert Spaces

In this article, we consider the preconditioned Hamiltonian Monte Carlo ...
research
04/10/2023

When does Metropolized Hamiltonian Monte Carlo provably outperform Metropolis-adjusted Langevin algorithm?

We analyze the mixing time of Metropolized Hamiltonian Monte Carlo (HMC)...

Please sign up or login with your details

Forgot password? Click here to reset