English

Weak Convergence Rates of Population versus Single-Chain Stochastic Approximation MCMC Algorithms

Statistics Theory 2013-10-29 v1 Statistics Theory

Abstract

In this paper, we establish the theory of weak convergence (toward a normal distribution) for both single-chain and population stochastic approximation MCMC algorithms. Based on the theory, we give an explicit ratio of convergence rates for the population SAMCMC algorithm and the single-chain SAMCMC algorithm. Our results provide a theoretic guarantee that the population SAMCMC algorithms are asymptotically more efficient than the single-chain SAMCMC algorithms when the gain factor sequence decreases slower than O(1/t), where t indexes the number of iterations. This is of interest for practical applications.

Keywords

Cite

@article{arxiv.1310.7479,
  title  = {Weak Convergence Rates of Population versus Single-Chain Stochastic Approximation MCMC Algorithms},
  author = {Qifan Song and Mingqi Wu and Faming Liang},
  journal= {arXiv preprint arXiv:1310.7479},
  year   = {2013}
}

Comments

36 pages

R2 v1 2026-06-22T01:55:33.018Z