Sufficient Conditions for Ergodicity and Convergence of MH, SA, and EM Algorithms

DOI10.1081/STM-120034128zbMath1068.65017MaRDI QIDQ3157855

D. S. B. Martins Neto, Chang Chung Yu Dorea, André G. C. Pereira

Publication date: 19 January 2005

Published in: Stochastic Models (Search for Journal in Brave)

zbMATH Keywords

simulated annealingMetropolis-Hastings algorithmsexpectation maximizationergodicity of Markov chainsDoeblin's ergodocity principleMonte Carlo Markov Chains algorithms

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Numerical analysis or methods applied to Markov chains (65C40)

Related Items (1)

Multistage Markov Chain Modeling of the Genetic Algorithm and Convergence Results

Cites Work

• Markov chains and stochastic stability
• Nonstationary Markov chains and convergence of the annealing algorithm
• Simple conditions for the convergence of the Gibbs sampler and Metropolis-Hastings algorithms
• The stochastic EM algorithm: Estimation and asymptotic results
• Markov chains for exploring posterior distributions. (With discussion)
• Cooling Schedules for Optimal Annealing
• Simple conditions for the convergence of simulated annealing type algorithms

This page was built for publication: Sufficient Conditions for Ergodicity and Convergence of MH, SA, and EM Algorithms