Sequentially interacting Markov chain Monte Carlo methods

DOI10.1214/09-AOS747zbMATH Open1251.65002arXiv1211.2582OpenAlexW2062758445MaRDI QIDQ620553FDOQ620553

Authors: Anthony E. Brockwell, Pierre Del Moral, Arnaud Doucet 

Publication date: 19 January 2011

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: Sequential Monte Carlo (SMC) is a methodology for sampling approximately from a sequence of probability distributions of increasing dimension and estimating their normalizing constants. We propose here an alternative methodology named Sequentially Interacting Markov Chain Monte Carlo (SIMCMC). SIMCMC methods work by generating interacting non-Markovian sequences which behave asymptotically like independent Metropolis-Hastings (MH) Markov chains with the desired limiting distributions. Contrary to SMC, SIMCMC allows us to iteratively improve our estimates in an MCMC-like fashion. We establish convergence results under realistic verifiable assumptions and demonstrate its performance on several examples arising in Bayesian time series analysis.

Full work available at URL: https://arxiv.org/abs/1211.2582

Recommendations

• Interacting sequential Monte Carlo samplers for trans-dimensional simulation
• Sequential Monte Carlo Samplers
• Stability of sequential Markov Chain Monte Carlo methods
• An adaptive sequential Monte Carlo sampler
• Sequential Monte Carlo samplers with independent Markov chain Monte Carlo proposals

zbMATH Keywords

convergencenumerical examplesMarkov chain Monte Carlo methodstate-space modelssequential Monte Carlo methodBayesian time seriesMetropolis-Hastings Markov chainsnormalizing constants

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Bayesian inference (62F15) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Discrete-time Markov processes on general state spaces (60J05)

Cites Work

• Sequential Monte Carlo Methods in Practice
• Sequential Monte Carlo Samplers
• Title not available (Why is that?)
• Filtering via Simulation: Auxiliary Particle Filters
• Title not available (Why is that?)
• Monte Carlo strategies in scientific computing
• A sequential particle filter method for static models
• Sequential Monte Carlo Methods for Dynamic Systems
• Equi-energy sampler with applications in statistical inference and statistical mechanics
• Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
• On the ergodicity properties of some adaptive MCMC algorithms
• Rates of convergence of the Hastings and Metropolis algorithms
• Following a moving target -- Monte Carlo inference for dynamic Bayesian models
• A Liapounov bound for solutions of the Poisson equation
• Diagnostics for Time Series Analysis
• Non-linear Markov Chain Monte Carlo
• Fluctuations of interacting Markov chain Monte Carlo methods
• Interacting Markov chain Monte Carlo methods for solving nonlinear measure-valued equations
• On convergence of chains with occupational self–interactions

Cited In (27)

• Title not available (Why is that?)
• Sequential estimation of temporally evolving latent space network models
• Layered adaptive importance sampling
• A central limit theorem for adaptive and interacting Markov chains
• An Invitation to Sequential Monte Carlo Samplers
• A Sequential Markov Chain Monte Carlo Approach to Set-up Adjustment of a Process over a Set of Lots
• Without-replacement sampling for particle methods on finite state spaces
• Fluctuations of interacting Markov chain Monte Carlo methods
• Self-Interacting Markov Chains: Some Asymptotics
• Transdimensional sequential Monte Carlo using variational Bayes -- SMCVB
• Sequential Monte Carlo Samplers
• Interacting Markov chain Monte Carlo methods for solving nonlinear measure-valued equations
• A new class of interacting Markov chain Monte Carlo methods
• Bayesian statistics with a smile: a resampling-sampling perspective
• Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
• Sequential Monte Carlo with Highly Informative Observations
• Stability of sequential Markov Chain Monte Carlo methods
• Conditional sequential Monte Carlo in high dimensions
• Non-asymptotic error bounds for sequential MCMC methods
• Properties of marginal sequential Monte Carlo methods
• Efficient sequential Monte Carlo algorithms for integrated population models
• On nonlinear Markov chain Monte Carlo
• A general theory of particle filters in hidden Markov models and some applications
• Limit theorems for sequential MCMC methods
• Interacting sequential Monte Carlo samplers for trans-dimensional simulation
• Quantitative approximations of evolving probability measures and sequential Markov chain Monte Carlo methods
• Sequential Monte Carlo methods for mixtures with normalized random measures with independent increments priors

This page was built for publication: Sequentially interacting Markov chain Monte Carlo methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q620553)