Couplings for Multinomial Hamiltonian Monte Carlo

04/11/2021
by   Kai Xu, et al.
0

Hamiltonian Monte Carlo (HMC) is a popular sampling method in Bayesian inference. Recently, Heng Jacob (2019) studied Metropolis HMC with couplings for unbiased Monte Carlo estimation, establishing a generic parallelizable scheme for HMC. However, in practice a different HMC method, multinomial HMC, is considered as the go-to method, e.g. as part of the no-U-turn sampler. In multinomial HMC, proposed states are not limited to end-points as in Metropolis HMC; instead points along the entire trajectory can be proposed. In this paper, we establish couplings for multinomial HMC, based on optimal transport for multinomial sampling in its transition. We prove an upper bound for the meeting time - the time it takes for the coupled chains to meet - based on the notion of local contractivity. We evaluate our methods using three targets: 1,000 dimensional Gaussians, logistic regression and log-Gaussian Cox point processes. Compared to Heng Jacob (2019), coupled multinomial HMC generally attains a smaller meeting time, and is more robust to choices of step sizes and trajectory lengths, which allows re-use of existing adaptation methods for HMC. These improvements together paves the way for a wider and more practical use of coupled HMC methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/23/2019

A Condition Number for Hamiltonian Monte Carlo

Hamiltonian Monte Carlo is a popular sampling technique for smooth targe...
research
10/20/2017

Zero Variance and Hamiltonian Monte Carlo Methods in GARCH Models

In this paper, we develop Bayesian Hamiltonian Monte Carlo methods for i...
research
03/28/2023

Hessian-informed Hamiltonian Monte Carlo for high-dimensional problems

We investigate the effect of using local and non-local second derivative...
research
08/12/2022

Bayesian Inference with Latent Hamiltonian Neural Networks

When sampling for Bayesian inference, one popular approach is to use Ham...
research
01/03/2019

Learning Nonlinear State Space Models with Hamiltonian Sequential Monte Carlo Sampler

State space models (SSM) have been widely applied for the analysis and v...
research
07/07/2023

On the convergence of dynamic implementations of Hamiltonian Monte Carlo and No U-Turn Samplers

There is substantial empirical evidence about the success of dynamic imp...
research
01/29/2016

On the Geometric Ergodicity of Hamiltonian Monte Carlo

We establish general conditions under which Markov chains produced by th...

Please sign up or login with your details

Forgot password? Click here to reset