Design of Hamiltonian Monte Carlo for perfect simulation of general continuous distributions

12/23/2022
by   George M. Leigh, et al.
0

Hamiltonian Monte Carlo (HMC) is an efficient method of simulating smooth distributions and has motivated the widely used No-U-turn Sampler (NUTS) and software Stan. We build on NUTS and the technique of "unbiased sampling" to design HMC algorithms that produce perfect simulation of general continuous distributions that are amenable to HMC. Our methods enable separation of Markov chain Monte Carlo convergence error from experimental error, and thereby provide much more powerful MCMC convergence diagnostics than current state-of-the-art summary statistics which confound these two errors. Objective comparison of different MCMC algorithms is provided by the number of derivative evaluations per perfect sample point. We demonstrate the methodology with applications to normal, t and normal mixture distributions up to 100 dimensions, and a 12-dimensional Bayesian Lasso regression. HMC runs effectively with a goal of 20 to 30 points per trajectory. Numbers of derivative evaluations per perfect sample point range from 390 for a univariate normal distribution to 12,000 for a 100-dimensional mixture of two normal distributions with modes separated by six standard deviations, and 22,000 for a 100-dimensional t-distribution with four degrees of freedom.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/17/2017

Pseudo-extended Markov chain Monte Carlo

Sampling from the posterior distribution using Markov chain Monte Carlo ...
research
09/23/2022

hdtg: An R package for high-dimensional truncated normal simulation

Simulating from the multivariate truncated normal distribution (MTN) is ...
research
08/14/2023

Perfect simulation from unbiased simulation

We show that any application of the technique of unbiased simulation bec...
research
07/13/2021

IID Sampling from Intractable Distributions

We propose a novel methodology for drawing iid realizations from any tar...
research
05/30/2017

Zonotope hit-and-run for efficient sampling from projection DPPs

Determinantal point processes (DPPs) are distributions over sets of item...
research
10/22/2021

Focusing on Difficult Directions for Learning HMC Trajectory Lengths

Hamiltonian Monte Carlo (HMC) is a premier Markov Chain Monte Carlo (MCM...
research
09/02/2023

Marginalised Normal Regression: Unbiased curve fitting in the presence of x-errors

The history of the seemingly simple problem of straight line fitting in ...

Please sign up or login with your details

Forgot password? Click here to reset