On convergence of properly weighted samples to the target distribution

DOI10.1016/J.JSPI.2007.05.030MaRDI QIDQ2474400zbMATH OpenOpenAlexFDO

Authors Sonia Malefaki, George Iliopoulos

Publication date 6 March 2008

Published in Journal of Statistical Planning and Inference (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/math/0505045

zbMATH Keywords

convergenceimportance samplinglimit distributionMarkov chain Monte Carlo methodMetropolis-Hastings algorithmproperly weighted samplessemi-Markov process

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Markov renewal processes, semi-Markov processes (60K15) Sampling theory, sample surveys (62D05) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)

Abstract: We consider importance sampling as well as other properly weighted samples with respect to a target distribution $pi$ from a different point of view. By considering the associated weights as sojourn times until the next jump, we define appropriate jump processes. When the original sample sequence forms an ergodic Markov chain, the associated jump process is an ergodic semi--Markov process with stationary distribution $pi$. Hence, the type of convergence of properly weighted samples may be stronger than that of weighted means. In particular, when the samples are independent and the mean weight is bounded above, we describe a slight modification in order to achieve exact (weighted) samples from the target distribution.

Recommendations

• Improved Sampling‐Importance Resampling and Reduced Bias Importance Sampling
• Weighted Average Importance Sampling and Defensive Mixture Distributions
• On the convergence of the Metropolis-Hastings Markov chains
• Monte Carlo methods for improper target distributions
• Convergence of adaptive mixtures of importance sampling schemes

Cites work

• A Theory for Dynamic Weighting in Monte Carlo Computation
• Equation of state calculations by fast computing machines
• Equilibrium measures for semi-Markov processes
• scientific article; zbMATH DE number 3913478 (Why is no real title available?)
• scientific article; zbMATH DE number 1350773 (Why is no real title available?)
• scientific article; zbMATH DE number 3349081 (Why is no real title available?)
• Monte Carlo sampling methods using Markov chains and their applications
• Monte Carlo strategies in scientific computing
• Rates of convergence of the Hastings and Metropolis algorithms
• Semi-Markov processes and reliability
• Sequential Monte Carlo Methods for Dynamic Systems

Cited in

(7)

• Jump Markov chains and rejection-free Metropolis algorithms
• A vanilla Rao-Blackwellization of Metropolis-Hastings algorithms
• Simulation from a Target Distribution Based on Discretization and Weighting
• Rao–Blackwellisation in the Markov Chain Monte Carlo Era
• The importance Markov chain
• Variance reduction of estimators arising from Metropolis-Hastings algorithms
• Limit theorems for weighted samples with applications to sequential Monte Carlo methods

This page was built for publication: On convergence of properly weighted samples to the target distribution

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2474400)