Accelerating parallel tempering: quantile tempering algorithm (QuanTA)
From MaRDI portal
Abstract: Using MCMC to sample from a target distribution, on a -dimensional state space can be a difficult and computationally expensive problem. Particularly when the target exhibits multimodality, then the traditional methods can fail to explore the entire state space and this results in a bias sample output. Methods to overcome this issue include the parallel tempering algorithm which utilises an augmented state space approach to help the Markov chain traverse regions of low probability density and reach other modes. This method suffers from the curse of dimensionality which dramatically slows the transfer of mixing information from the auxiliary targets to the target of interest as . This paper introduces a novel prototype algorithm, QuanTA, that uses a Gaussian motivated transformation in an attempt to accelerate the mixing through the temperature schedule of a parallel tempering algorithm. This new algorithm is accompanied by a comprehensive theoretical analysis quantifying the improved efficiency and scalability of the approach; concluding that under weak regularity conditions the new approach gives accelerated mixing through the temperature schedule. Empirical evidence of the effectiveness of this new algorithm is illustrated on canonical examples.
Recommendations
- Generalized parallel tempering on Bayesian inverse problems
- Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
- Analysis and optimization of certain parallel Monte Carlo methods in the low temperature limit
- Weighted particle tempering
- Adaptive Markov chain Monte Carlo for auxiliary variable method and its application to parallel tempering
Cites work
- A general framework for the parametrization of hierarchical models
- A Stochastic Approximation Method
- Accurate Approximations for Posterior Moments and Marginal Densities
- Algorithm AS 136: A K-Means Clustering Algorithm
- Annealing Markov Chain Monte Carlo with Applications to Ancestral Inference
- Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
- Combination of factorial methods and cluster analysis in \textsf{R}: the package \texttt{FactoClass}
- Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
- Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
- Efficient Construction of Reversible Jump Markov Chain Monte Carlo Proposal Distributions
- Equi-energy sampler with applications in statistical inference and statistical mechanics
- Error bounds for sequential Monte Carlo samplers for multimodal distributions
- Error bounds for the Laplace approximation for definite integrals
- scientific article; zbMATH DE number 4100386 (Why is no real title available?)
- scientific article; zbMATH DE number 43570 (Why is no real title available?)
- Markov chains for exploring posterior distributions. (With discussion)
- Minimising MCMC variance via diffusion limits, with an application to simulated tempering
- Non-asymptotic error bounds for sequential MCMC methods
- Optimal scaling for various Metropolis-Hastings algorithms.
- Probability. Theory and examples.
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- Simple approximate MAP inference for Dirichlet processes mixtures
- Sufficient conditions for torpid mixing of parallel and simulated tempering
- The elements of statistical learning. Data mining, inference, and prediction
- Towards optimal scaling of Metropolis-coupled Markov chain Monte Carlo
- Variable selection in clustering via Dirichlet process mixture models
- Weak convergence and optimal scaling of random walk Metropolis algorithms
- Weight-preserving simulated tempering
Cited in
(15)- Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
- State-dependent swap strategies and automatic reduction of number of temperatures in adaptive parallel tempering algorithm
- Weighted particle tempering
- Generalized parallel tempering on Bayesian inverse problems
- Anytime parallel tempering
- Spectral gap of replica exchange Langevin diffusion on mixture distributions
- Adaptive Markov chain Monte Carlo for auxiliary variable method and its application to parallel tempering
- Parallel tempering for dynamic generalized linear models
- Adaptive regularisation for ensemble Kalman inversion
- Skew Brownian motion and complexity of the ALPS algorithm
- Accelerating adaptation in the adaptive Metropolis–Hastings random walk algorithm
- Accelerate Langevin sampling with birth-death process and exploration component
- Convergence speed and approximation accuracy of numerical MCMC
- Tuning tempered transitions
- Parallel tempering with equi-energy moves
This page was built for publication: Accelerating parallel tempering: quantile tempering algorithm (QuanTA)
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5203957)
