Mode jumping proposals in MCMC
Markov chain Monte Carlo (MCMC) algorithms allow the generation of samples from a specified target distribution. The Metropolis-Hastings setup gives a general framework for the specification of the Markov chain and each iteration consists of two parts. First, with \(x\) denoting the current state, a potential new state, \(y,\) is generated according to a specified proposal kernel, \(q(y/x),\) and, second, \(y\) is accepted with a given probability, \(\alpha(y/x).\) NEWLINENEWLINENEWLINEThe paper defines a new scheme, within the Metropolis-Hastings class, for the construction of MCMC algorithms and demonstrates how this allows local optimization be to incorporated in the MCMC procedures. Recipes for handling multimedia distributions are given and their potential are illustrated by three examples. The attention is limited to continuous distributions because mode jumping proposals are not directly applicable for discrete distributions. The continuous distributions on \(\mathbb{R}^{n}\) are considered and it is specified how an optimization for local maxima of the target distribution can be incorporated in the specification of the Markov chain. A chain with frequent jumps between modes is obtained.
- Improving the acceptance rate of reversible jump MCMC proposals
- Mode jumping MCMC for Bayesian variable selection in GLMM
- Reversible jump MCMC
- Adaptive proposal construction for reversible jump MCMC
- Reversible jump Markov chain Monte Carlo computation and Bayesian model determination
- Efficient Construction of Reversible Jump Markov Chain Monte Carlo Proposal Distributions
- scientific article; zbMATH DE number 6378055
- Markov chain Monte Carlo methods for switching diffusion models
- Adaptive independent Metropolis-Hastings
- A Repelling–Attracting Metropolis Algorithm for Multimodality
- Mode jumping MCMC for Bayesian variable selection in GLMM
- A Metropolis-class sampler for targets with non-convex support
- Hopping between distant basins
- A subsampling approach for Bayesian model selection
- Penalised t-walk MCMC
- A framework for adaptive MCMC targeting multimodal distributions
- Generalized darting Monte Carlo
- Weight-preserving simulated tempering
- A multiple-try Metropolis-Hastings algorithm with tailored proposals
- Recent progress on reservoir history matching: a review
- On the flexibility of Metropolis-Hastings acceptance probabilities in auxiliary variable proposal generation
- On the Use of Local Optimizations within Metropolis–Hastings Updates
- Bayesian Analysis of the Scatterometer Wind Retrieval Inverse Problem: Some New Approaches
- Uncertainty analysis for computationally expensive models with multiple outputs
- Parallel generalized elliptical slice sampling with adaptive regional pseudo-priors
- Generating weighted MAX-2-SAT instances with frustrated loops: an RBM case study
- Metropolized randomized maximum likelihood for improved sampling from multimodal distributions
- Control Variates for the Metropolis–Hastings Algorithm
- A Mode-Jumping Algorithm for Bayesian Factor Analysis
- Monte Carlo Approximation of Bayes Factors via Mixing With Surrogate Distributions
- Global Likelihood Sampler for Multimodal Distributions
- Sampling using adaptive regenerative processes
- Model choice using reversible jump Markov chain Monte Carlo
- Accelerate Langevin sampling with birth-death process and exploration component
- Multimodal sampling via approximate symmetries
- Explainable Bayesian deep learning through input-skip latent binary Bayesian neural networks
This page was built for publication: Mode jumping proposals in MCMC
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2722311)
