DeepAI AI Chat
Log In Sign Up

Quasi Markov Chain Monte Carlo Methods

by   Tobias Schwedes, et al.

Quasi-Monte Carlo (QMC) methods for estimating integrals are attractive since the resulting estimators converge at a faster rate than pseudo-random Monte Carlo. However, they can be difficult to set up on arbitrary posterior densities within the Bayesian framework, in particular for inverse problems. We introduce a general parallel Markov chain Monte Carlo (MCMC) framework, for which we prove a law of large numbers and a central limit theorem. We further extend this approach to the use of adaptive kernels and state conditions, under which ergodicity holds. As a further extension, an importance sampling estimator is derived, for which asymptotic unbiasedness is proven. We consider the use of completely uniformly distributed (CUD) numbers and non-reversible transitions within the above stated methods, which leads to a general parallel quasi-MCMC (QMCMC) methodology. We prove consistency of the resulting estimators and demonstrate numerically that this approach scales close to n^-1 as we increase parallelisation, instead of the usual n^-1/2 that is typical of standard MCMC algorithms. In practical statistical models we observe up to 2 orders of magnitude improvement compared with pseudo-random methods.


page 1

page 2

page 3

page 4


Markov chain Monte Carlo importance samplers for Bayesian models with intractable likelihoods

We consider the efficient use of an approximation within Markov chain Mo...

An MCMC Approach to Classical Estimation

This paper studies computationally and theoretically attractive estimato...

A table of short-period Tausworthe generators for Markov chain quasi-Monte Carlo

We consider the problem of estimating expectations by using Markov chain...

Efficient adaptive MCMC implementation for Pseudo-Bayesian quantum tomography

We revisit the Pseudo-Bayesian approach to the problem of estimating den...

Air Markov Chain Monte Carlo

We introduce a class of Adapted Increasingly Rarely Markov Chain Monte C...

Reversible Jump Metropolis Light Transport using Inverse Mappings

We study Markov Chain Monte Carlo (MCMC) methods operating in primary sa...