Weak Convergence Rates of Population Versus Single-Chain Stochastic Approximation MCMC Algorithms
From MaRDI portal
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.
Recommendations
- Convergence rates of attractive-repulsive MCMC algorithms
- On the convergence rates of some adaptive Markov chain Monte Carlo algorithms
- Convergence rates of two-component MCMC samplers
- Weak convergence of Markov chain sampling methods and annealing algorithms to diffusions
- Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms
- scientific article; zbMATH DE number 472933
- Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
Cites work
- A stochastic approximation algorithm with Markov chain Monte-Carlo method for incomplete data estimation problems
- A Stochastic Approximation Method
- An adaptive Metropolis algorithm
- Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
- Dynamic weighting in Monte Carlo and optimization
- Explicit solution of the Lyapunov-matrix equation
- General Irreducible Markov Chains and Non-Negative Operators
- Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
- scientific article; zbMATH DE number 3723610 (Why is no real title available?)
- scientific article; zbMATH DE number 46578 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 1471711 (Why is no real title available?)
- Improving SAMC using smoothing methods: Theory and applications to Bayesian model selection problems
- Learning Bayesian networks for discrete data
- Limit theorems for some adaptive MCMC algorithms with subgeometric kernels
- Markov chains and stochastic stability
- Mixing times for uniformly ergodic Markov chains
- Monte Carlo sampling methods using Markov chains and their applications
- On the ergodicity properties of some adaptive MCMC algorithms
- Parametric inference for imperfectly observed Gibbsian fields
- Real-Parameter Evolutionary Monte Carlo With Applications to Bayesian Mixture Models
- Stability of Stochastic Approximation under Verifiable Conditions
- Stochastic Approximation in Monte Carlo Computation
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- The Multiple-Try Method and Local Optimization in Metropolis Sampling
- Trajectory averaging for stochastic approximation MCMC algorithms
- Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
Cited in
(7)- Parallel and interacting stochastic approximation annealing algorithms for global optimisation
- Double-parallel Monte Carlo for Bayesian analysis of big data
- Bayesian neural networks for selection of drug sensitive genes
- Consistent Sparse Deep Learning: Theory and Computation
- Energy-Based Models with Applications to Speech and Language Processing
- An overview of stochastic approximation Monte Carlo
- Times Square Sampling: An Adaptive Algorithm for Free Energy Estimation
This page was built for publication: Weak Convergence Rates of Population Versus Single-Chain Stochastic Approximation MCMC Algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2939266)
