Tuning tempered transitions
From MaRDI portal
Abstract: The method of tempered transitions was proposed by Neal (1996) for tackling the difficulties arising when using Markov chain Monte Carlo to sample from multimodal distributions. In common with methods such as simulated tempering and Metropolis-coupled MCMC, the key idea is to utilise a series of successively easier to sample distributions to improve movement around the state space. Tempered transitions does this by incorporating moves through these less modal distributions into the MCMC proposals. Unfortunately the improved movement between modes comes at a high computational cost with a low acceptance rate of expensive proposals. We consider how the algorithm may be tuned to increase the acceptance rates for a given number of temperatures. We find that the commonly assumed geometric spacing of temperatures is reasonable in many but not all applications.
Recommendations
- Towards optimal scaling of Metropolis-coupled Markov chain Monte Carlo
- Weight-preserving simulated tempering
- Accelerating parallel tempering: quantile tempering algorithm (QuanTA)
- Perfect Forward Simulation via Simulated Tempering
- Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
Cites work
- A path sampling identity for computing the Kullback-Leibler and J divergences
- A slowly mixing Markov chain with implications for Gibbs sampling
- Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
- Computational and Inferential Difficulties with Mixture Posterior Distributions
- Estimating Bayes factors via thermodynamic integration and population MCMC
- scientific article; zbMATH DE number 1350773 (Why is no real title available?)
- scientific article; zbMATH DE number 1085980 (Why is no real title available?)
- Marginal Likelihood Estimation via Power Posteriors
- Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling
- Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
Cited in
(14)- State-dependent swap strategies and automatic reduction of number of temperatures in adaptive parallel tempering algorithm
- Distance between configurations in Markov chain Monte Carlo simulations
- Normalizing constants of log-concave densities
- Consistency of variational Bayes inference for estimation and model selection in mixtures
- Weight-preserving simulated tempering
- Thermodynamic Bayesian model comparison
- A path sampling identity for computing the Kullback-Leibler and J divergences
- scientific article; zbMATH DE number 1633754 (Why is no real title available?)
- A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines
- Adaptive regularisation for ensemble Kalman inversion
- Estimating the evidence -- a review
- Adaptive posterior concentration rates for sparse high-dimensional linear regression with random design and unknown error variance
- Parallel tempering with equi-energy moves
- Improving power posterior estimation of statistical evidence
This page was built for publication: Tuning tempered transitions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q746180)
