On the ergodicity properties of some adaptive MCMC algorithms
arXiv:math/0610317 · doi:10.1214/105051606000000286
Abstract
In this paper we study the ergodicity properties of some adaptive Markov chain Monte Carlo algorithms (MCMC) that have been recently proposed in the literature. We prove that under a set of verifiable conditions, ergodic averages calculated from the output of a so-called adaptive MCMC sampler converge to the required value and can even, under more stringent assumptions, satisfy a central limit theorem. We prove that the conditions required are satisfied for the independent Metropolis--Hastings algorithm and the random walk Metropolis algorithm with symmetric increments. Finally, we propose an application of these results to the case where the proposal distribution of the Metropolis--Hastings update is a mixture of distributions from a curved exponential family.
Published at http://dx.doi.org/10.1214/105051606000000286 in the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)
References in corpus (2)
Cited by in corpus (74)
- On the ergodicity properties of some adaptive MCMC algorithms
- Dimension-independent likelihood-informed MCMC
- Likelihood-informed dimension reduction for nonlinear inverse problems
- An introduction to sampling via measure transport
- Improved Adaptive Rejection Metropolis Sampling Algorithms
- Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
- Transport map accelerated Markov chain Monte Carlo
- Adaptive tempered reversible jump algorithm for Bayesian curve fitting
- On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
- Dynamical Masses of Eps Ind B and C: Two Massive Brown Dwarfs at the Edge of the Stellar-Substellar Boundary
- Sequentially interacting Markov chain Monte Carlo methods
- On perturbed proximal gradient algorithms
- Adaptive Gibbs samplers and related MCMC methods
- On the stability and ergodicity of adaptive scaling Metropolis algorithms
- Consistency of Markov chain quasi-Monte Carlo on continuous state spaces
- Bayesian neural networks via MCMC: a Python-based tutorial
- A multi-point Metropolis scheme with generic weight functions
- Inferring large graphs using l1-penalized likelihood
- Bayesian Inversion for Anisotropic Hydraulic Phase-Field Fracture
- A Mixture-Based Approach to Regional Adaptation for MCMC
- On nonlinear Markov chain Monte Carlo
- Estimating Discrete Markov Models From Various Incomplete Data Schemes
- Analysis of nonsmooth stochastic approximation: the differential inclusion approach
- Computation for Latent Variable Model Estimation: A Unified Stochastic Proximal Framework
- Kernel estimators of asymptotic variance for adaptive Markov chain Monte Carlo
- Inferring the photometric and size evolution of galaxies from image simulations
- Accelerating MCMC via Parallel Predictive Prefetching
- Approximating Probability Densities by Iterated Laplace Approximations
- Markovian stochastic approximation with expanding projections
- On the Stability of Sequential Monte Carlo Methods in High Dimensions
- Bayesian computation: a perspective on the current state, and sampling backwards and forwards
- Grapham: Graphical Models with Adaptive Random Walk Metropolis Algorithms
- A cautionary tale on the efficiency of some adaptive Monte Carlo schemes
- Accelerated dimension-independent adaptive Metropolis
- Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
- Stability of adversarial Markov chains, with an application to adaptive MCMC algorithms
- SCoPE: An efficient method of Cosmological Parameter Estimation
- Trajectory averaging for stochastic approximation MCMC algorithms
- Bayesian epidemiological modeling over high-resolution network data
- Policy-guided Monte Carlo on general state spaces: Application to glass-forming mixtures
- Adaptive parallel tempering algorithm
- On the stability of some controlled Markov chains and its applications to stochastic approximation with Markovian dynamic
- ParaDRAM: A Cross-Language Toolbox for Parallel High-Performance Delayed-Rejection Adaptive Metropolis Markov Chain Monte Carlo Simulations
- A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions
- Multilevel Dimension-Independent Likelihood-Informed MCMC for Large-Scale Inverse Problems
- On the Convergence of Adaptive Sequential Monte Carlo Methods
- A fast and recursive algorithm for clustering large datasets with -medians
- Resampling from the past to improve on MCMC algorithms
- Channel Tracking for Relay Networks via Adaptive Particle MCMC
- Adaptive Monte Carlo augmented with normalizing flows
- Replica exchange nested sampling
- Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
- A Strong Law of Large Numbers for Strongly Mixing Processes
- Quasi Markov Chain Monte Carlo Methods
- Note on the computation of the Metropolis-Hastings ratio for Birth-or-Death moves in trans-dimensional MCMC algorithms for signal decomposition problems
- Parallel Tempering on Optimized Paths
- Almost sure convergence rates of adaptive increasingly rare Markov chain Monte Carlo
- Discussion of "Riemann manifold Langevin and Hamiltonian Monte Carlo methods'' by M. Girolami and B. Calderhead
- Finite Sample Properties of Adaptive Markov Chains via Curvature
- A Geometric View of Posterior Approximation
- A copula based approach to adaptive sampling
- Adaptive Independent Metropolis-Hastings by Fast Estimation of Mixtures of Normals
- Bayesian Robust Quantile Regression
- Fluctuations of Interacting Markov Chain Monte Carlo Methods
- Weak convergence of adaptive Markov chain Monte Carlo
- f-SAEM: A fast Stochastic Approximation of the EM algorithm for nonlinear mixed effects models
- Extracting the Italian output gap: a Bayesian approach
- Adaptive Markov Chain Monte Carlo for Auxiliary Variable Method and Its Application to Parallel Tempering
- Entropy-based adaptive Hamiltonian Monte Carlo
- Adaptive Metropolis-Hastings Sampling using Reversible Dependent Mixture Proposals
- Robust adaptive Metropolis algorithm with coerced acceptance rate
- Calibration and filtering for multi factor commodity models with seasonality: incorporating panel data from futures contracts
- Population-Based Reversible Jump Markov Chain Monte Carlo
- Adaptive Metropolis Algorithm Using Variational Bayesian Adaptive Kalman Filter