Adaptive proposal distribution for random walk Metropolis algorithm
From MaRDI portal
Here, a new adaptive Markov Chain Monte Carlo method (MCMC) is introduced that yields a quick and flexible tool for estimating e.g. posteriori distributions in parameter estimation problems. Basically the method consists of the well-known Metropolis algorithm [see \textit{W.K. Hastings}, Biometrika 57, 97-109 (1970; Zbl 0219.65008)], where, however, the proposal distribution is tuned along the search according to the covariance calculated from a fixed number of previous states. This procedure makes sure that the MCMC process adapts to the target distribution, at least locally, and thus keeps the search effective all the time. The authors call this method Adaptive Proposal (AP). This paper is devoted to investigate the properties and practical usefulness of the AP algorithm. Although the stationary distribution of the AP algorithm is slightly biased, it appears to provide an efficient tool for, e.g., reasonable low-dimensional problems, as typically encountered in nonlinear regression problems in natural sciences. The AP algorithm is also applied in more realistic inverse problems applications. This problem arises in data processing of the Global Ozone Monitoring by Occultation of Stars satellite instruments. In this interesting application each analysis requires about 50 inversions. Moreover, when applying the Metropolis-Hastings method each inversion requires a quite individual proposal distribution. It appears that AP provides a valuable tool for this kind of applications.
Recommendations
- Adaptive independent Metropolis-Hastings
- On an adaptive version of the Metropolis–Hastings algorithm with independent proposal distribution
- Optimal proposal distributions and adaptive MCMC
- On adaptive Metropolis-Hastings methods
- Accelerating adaptation in the adaptive Metropolis–Hastings random walk algorithm
Cites work
- Adaptive Markov Chain Monte Carlo through Regeneration
- Adaptive proposal distribution for random walk Metropolis algorithm
- Adaptive Rejection Metropolis Sampling within Gibbs Sampling
- Adaptive Rejection Sampling for Gibbs Sampling
- An adaptive Metropolis algorithm
- Equation of state calculations by fast computing machines
- scientific article; zbMATH DE number 849920 (Why is no real title available?)
- scientific article; zbMATH DE number 274399 (Why is no real title available?)
- Monte Carlo sampling methods using Markov chains and their applications
- Sampling-Based Approaches to Calculating Marginal Densities
- Self-regenerative Markov chain Monte Carlo with adaptation
- Weak convergence and optimal scaling of random walk Metropolis algorithms
Cited in
(87)- Adaptive proposal distribution for random walk Metropolis algorithm
- bayescopulareg
- Ordering and improving the performance of Monte Carlo Markov chains.
- Adaptive Metropolis algorithm using variational Bayesian adaptive Kalman filter
- Automated tuning for parameter identification and uncertainty quantification in multi-scale coronary simulations
- Extending approximate Bayesian computation methods to high dimensions via a Gaussian copula model
- Modeling host-seeking behavior of African malaria vector mosquitoes in the presence of long-lasting insecticidal nets
- Modified Cholesky Riemann manifold Hamiltonian Monte Carlo: exploiting sparsity for fast sampling of high-dimensional targets
- A method for estimating dominant acoustic backscatter mechanism of water-seabed interface via relative entropy estimation
- X-TMCMC: adaptive kriging for Bayesian inverse modeling
- Computational advances for and from Bayesian analysis
- Particle-based energetic variational inference
- Plateau proposal distributions for adaptive component-wise multiple-try metropolis
- Collective proposal distributions for nonlinear MCMC samplers: mean-field theory and fast implementation
- Randomized maximum likelihood based posterior sampling
- A new adaptive approach of the Metropolis-Hastings algorithm applied to structural damage identification using time domain data
- Bayesian inference of non-linear multiscale model parameters accelerated by a deep neural network
- Bayesian inversion for electrical-impedance tomography in medical imaging using the nonlinear Poisson-Boltzmann equation
- A novel approach for subsurface characterization of coupled fluid flow and geomechanical deformation: the case of slightly compressible flows
- Variance reduction for Markov chains with application to MCMC
- Oscillation of metropolis-Hastings and simulated annealing algorithms around LASSO estimator
- Generalized evolutionary point processes: model specifications and model comparison
- Bayesian inversion for anisotropic hydraulic phase-field fracture
- On the stability of some controlled Markov chains and its applications to stochastic approximation with Markovian dynamic
- Proposal adaptation in simulated annealing for continuous optimization problems
- On the flexibility of the design of multiple try Metropolis schemes
- Generalized multiple importance sampling
- Estimating fibres' material parameter distributions from limited data with the help of Bayesian inference
- Grapham: graphical models with adaptive random walk Metropolis algorithms
- A central limit theorem for adaptive and interacting Markov chains
- Componentwise adaptation for high dimensional MCMC
- Adaptive Metropolis-Hastings sampling using reversible dependent mixture proposals
- Most likely optimal subsampled Markov chain Monte Carlo
- Bayesian joint-quantile regression
- Variance reduction using nonreversible Langevin samplers
- Adaptive multiple importance sampling
- Bayesian parameter estimation and model selection for strongly nonlinear dynamical systems
- Adaptive Incremental Mixture Markov Chain Monte Carlo
- Adaptive Component-Wise Multiple-Try Metropolis Sampling
- Data revisions and DSGE models
- Parametrization of Random Vectors in Polynomial Chaos Expansions via Optimal Transportation
- Low-rank separated representation surrogates of high-dimensional stochastic functions: application in Bayesian inference
- An adaptive backward coupling Metropolis algorithm for truncated distributions
- Adaptive proposal construction for reversible jump MCMC
- Parallel hierarchical sampling: a general-purpose interacting Markov chains Monte Carlo algorithm
- On an adaptive version of the Metropolis–Hastings algorithm with independent proposal distribution
- Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
- An approach to periodic, time-varying parameter estimation using nonlinear filtering
- A mathematical model for the dynamics and MCMC analysis of tomato bacterial wilt disease
- Random sampling from joint probability distributions defined in a Bayesian framework
- Estimating structural credit risk models when market prices are contaminated with noise
- Markov Chain Monte Carlo Methods for High Dimensional Inversion in Remote Sensing
- Bayesian estimation and uncertainty quantification in models of urea hydrolysis byE. colibiofilms
- Modeling material stress using integrated Gaussian Markov random fields
- Random Forest Adjustment for Approximate Bayesian Computation
- A simulation smoother for long memory time series with correlated and heteroskedastic additive noise
- Sampling hyperparameters in hierarchical models: Improving on Gibbs for high-dimensional latent fields and large datasets
- Maximum likelihood estimation of Gaussian copula models for geostatistical count data
- Adaptive multiple importance sampling for Gaussian processes
- Hyperparameter optimization via sequential uniform designs
- An adaptive Metropolis algorithm
- Posterior inference on parameters of stochastic differential equations via non-linear Gaussian filtering and adaptive MCMC
- Intercorrelated random fields with bounds and the Bayesian identification of their parameters: Application to linear elastic struts and fibers
- A two-stage adaptive Metropolis algorithm
- Accelerating adaptation in the adaptive Metropolis–Hastings random walk algorithm
- Gradient-based adaptive importance samplers
- A point mass proposal method for Bayesian state-space model fitting
- Diffusion approximations and control variates for MCMC
- Deterministic sampling based on Kullback-Leibler divergence and its applications
- Accelerating MCMC algorithms
- Deterministic Sampling of Expensive Posteriors Using Minimum Energy Designs
- Modeling and Forecasting Macroeconomic Downside Risk
- Statistical Modeling of the Effectiveness of Preventive Maintenance for Repairable Systems
- Markov chain Monte Carlo methods applied to the stochastic inversion of 1D viscoelastic parameters
- Guided sequential ABC schemes for intractable Bayesian models
- A probabilistic diagnostic for Laplace approximations: introduction and experimentation
- An adaptive approach to Langevin MCMC
- Stratified distance space improves the efficiency of sequential samplers for approximate Bayesian computation
- Annealing strategies for variance reduction in balance heuristic estimators
- Sampling by divergence minimization
- Optimizing the diffusion coefficient of overdamped Langevin dynamics
- A Bayesian promotion time cure rate model with current status data
- Approximating evidence via bounded harmonic means
- Graph-accelerated Markov chain Monte Carlo using approximate samples
- Implementing componentwise Hastings algorithms
- Iterated importance sampling in missing data problems
- Convergence of adaptive mixtures of importance sampling schemes
This page was built for publication: Adaptive proposal distribution for random walk Metropolis algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q132585)
