Robust adaptive Metropolis algorithm with coerced acceptance rate
From MaRDI portal
Abstract: The adaptive Metropolis (AM) algorithm of Haario, Saksman and Tamminen [Bernoulli 7 (2001) 223-242] uses the estimated covariance of the target distribution in the proposal distribution. This paper introduces a new robust adaptive Metropolis algorithm estimating the shape of the target distribution and simultaneously coercing the acceptance rate. The adaptation rule is computationally simple adding no extra cost compared with the AM algorithm. The adaptation strategy can be seen as a multidimensional extension of the previously proposed method adapting the scale of the proposal distribution in order to attain a given acceptance rate. The empirical results show promising behaviour of the new algorithm in an example with Student target distribution having no finite second moment, where the AM covariance estimate is unstable. In the examples with finite second moments, the performance of the new approach seems to be competitive with the AM algorithm combined with scale adaptation.
Recommendations
- On adaptive Metropolis-Hastings methods
- Adaptive independent Metropolis-Hastings
- Can the adaptive Metropolis algorithm collapse without the covariance lower bound?
- Adaptive optimal scaling of Metropolis-Hastings algorithms using the Robbins-Monro process
- On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
Cites work
- scientific article; zbMATH DE number 5348356 (Why is no real title available?)
- scientific article; zbMATH DE number 5520724 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 1350773 (Why is no real title available?)
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 840151 (Why is no real title available?)
- An adaptive Metropolis algorithm
- Can the adaptive Metropolis algorithm collapse without the covariance lower bound?
- Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
- General state space Markov chains and MCMC algorithms
- Geometric ergodicity of Metropolis algorithms
- Grapham: graphical models with adaptive random walk Metropolis algorithms
- Limit theorems for some adaptive MCMC algorithms with subgeometric kernels
- MC's for MCMC'ists
- On adaptive Markov chain Monte Carlo algorithms
- On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
- On the ergodicity properties of some adaptive MCMC algorithms
- On the stability and ergodicity of adaptive scaling Metropolis algorithms
- Optimal scaling for various Metropolis-Hastings algorithms.
- Robust Statistics
- Stability of Stochastic Approximation under Verifiable Conditions
- Weak convergence and optimal scaling of random walk Metropolis algorithms
Cited in
(42)- Stochastic loss reserving with dependence: a flexible multivariate Tweedie approach
- Posterior inference on parameters of stochastic differential equations via non-linear Gaussian filtering and adaptive MCMC
- Wavelet shrinkage in nonparametric regression models with positive noise
- An ABC approach for CAViaR models with asymmetric kernels
- Adaptive Metropolis algorithm using variational Bayesian adaptive Kalman filter
- A probabilistic finite element method based on random meshes: a posteriori error estimators and Bayesian inverse problems
- Forecasting exchange rates using asymmetric losses: a Bayesian approach
- A novel method for estimating the common signals for consensus across multiple ranked lists
- An adaptive multiple-try Metropolis algorithm
- Stochastic epidemic models inference and diagnosis with Poisson random measure data augmentation
- Latent Space Modeling of Hypergraph Data
- A mathematical model for the dynamics and MCMC analysis of tomato bacterial wilt disease
- Bayesian parameter estimation for the Swift model of eye-movement control during reading
- Implications of quantal response statistical equilibrium
- Bayesian computation: a summary of the current state, and samples backwards and forwards
- Efficient and generalizable tuning strategies for stochastic gradient MCMC
- Automatically tuned general-purpose MCMC via new adaptive diagnostics
- Accelerated dimension-independent adaptive metropolis
- ramcmc
- adaptMCMC
- fmcmc
- scientific article; zbMATH DE number 7625170 (Why is no real title available?)
- Mitigating spatial confounding by explicitly correlating Gaussian random fields
- Point process models for sweat gland activation observed with noise
- Efficient Adaptive MCMC Through Precision Estimation
- Global sensitivity analysis for statistical model parameters
- Predicting observed and hidden extreme events in complex nonlinear dynamical systems with partial observations and short training time series
- Hybrid elicitation and quantile-parametrized likelihood
- Simultaneous transformation and rounding (STAR) models for integer-valued data
- Conditional particle filters with diffuse initial distributions
- Ergodicity of combocontinuous adaptive MCMC algorithms
- A data fusion approach for spatial analysis of speciated PM2.5 across time
- Deterministic Sampling of Expensive Posteriors Using Minimum Energy Designs
- f-SAEM: a fast stochastic approximation of the EM algorithm for nonlinear mixed effects models
- Adjoint Hamiltonian Monte Carlo algorithm for the estimation of elastic modulus through the inversion of elastic wave propagation data
- Geometric adaptive Monte Carlo in random environment
- A non-stationary model for spatially dependent circular response data based on wrapped Gaussian processes
- Can the adaptive Metropolis algorithm collapse without the covariance lower bound?
- Methods for computing numerical standard errors: review and application to value-at-risk estimation
- Emerging directions in Bayesian computation
- Sequentially guided MCMC proposals for synthetic likelihoods and correlated synthetic likelihoods
- Adaptive Component-Wise Multiple-Try Metropolis Sampling
This page was built for publication: Robust adaptive Metropolis algorithm with coerced acceptance rate
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q116440)
