Approximations of geometrically ergodic reversible Markov chains
From MaRDI portal
Abstract: A common tool in the practice of Markov Chain Monte Carlo is to use approximating transition kernels to speed up computation when the desired kernel is slow to evaluate or intractable. A limited set of quantitative tools exist to assess the relative accuracy and efficiency of such approximations. We derive a set of tools for such analysis based on the Hilbert space generated by the stationary distribution we intend to sample, . Our results apply to approximations of reversible chains which are geometrically ergodic, as is typically the case for applications to Markov Chain Monte Carlo. The focus of our work is on determining whether the approximating kernel will preserve the geometric ergodicity of the exact chain, and whether the approximating stationary distribution will be close to the original stationary distribution. For reversible chains, our results extend the results of Johndrow et al. [18] from the uniformly ergodic case to the geometrically ergodic case, under some additional regularity conditions. We then apply our results to a number of approximate MCMC algorithms.
Recommendations
- On the approximation of one Markov chain by another
- scientific article; zbMATH DE number 1560252
- Approximating Markov chains and \(V\)-geometric ergodicity via weak perturbation theory
- Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
- Approximate verification of geometric ergodicity for multiple-step Metropolis transition kernels
Cites work
- A note on geometric ergodicity and floating-point roundoff error
- Accurate Approximations for Posterior Moments and Marginal Densities
- Approximate Inference in Generalized Linear Mixed Models
- Approximating Markov chains and \(V\)-geometric ergodicity via weak perturbation theory
- Automated scalable Bayesian inference via Hilbert coresets
- Contributions to Doeblin's theory of Markov processes
- Convergence in the Wasserstein Metric for Markov Chain Monte Carlo Algorithms with Applications to Image Restoration
- Convergence Properties of Perturbed Markov Chains
- Explicit error bounds for Markov chain Monte Carlo
- General state space Markov chains and MCMC algorithms
- Geometric L2 and L1 convergence are equivalent for reversible Markov chains
- Geometric ergodicity and hybrid Markov chains
- Geometric ergodicity and R-positivity for general Markov chains
- Geometric ergodicity of Gibbs and block Gibbs samplers for a hierarchical random effects model
- Handbook of Markov Chain Monte Carlo
- scientific article; zbMATH DE number 4215168 (Why is no real title available?)
- scientific article; zbMATH DE number 1022519 (Why is no real title available?)
- scientific article; zbMATH DE number 1417211 (Why is no real title available?)
- Markov Chains
- Monte Carlo strategies in scientific computing.
- Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
- On the geometric ergodicity of Hamiltonian Monte Carlo
- Perturbation bounds for Monte Carlo within metropolis via restricted approximations
- Perturbation theory for Markov chains via Wasserstein distance
- Rates of convergence for everywhere-positive Markov chains
- Regular Perturbation of V-Geometrically Ergodic Markov Chains
- Renewal theory and computable convergence rates for geometrically erdgodic Markov chains
- Sensitivity and convergence of uniformly ergodic Markov chains
- Stability of noisy Metropolis-Hastings
- The pseudo-marginal approach for efficient Monte Carlo computations
Cited in
(14)- Geometric ergodicity of Rao and Teh's algorithm for Markov jump processes and CTBNs
- Perturbation bounds for Monte Carlo within metropolis via restricted approximations
- \(V\)-geometrical ergodicity of Markov kernels via finite-rank approximations
- Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
- Variance bounding and geometric ergodicity of Markov chain Monte Carlo kernels for approximate Bayesian computation
- Establishing some order amongst exact approximations of MCMCs
- Approximate verification of geometric ergodicity for multiple-step Metropolis transition kernels
- Geometric allocation approach for the transition kernel of a Markov chain
- Robustness of iterated function systems of Lipschitz maps
- Perturbation analysis of Markov chain Monte Carlo for graphical models
- Perturbation theory for killed Markov processes and quasi-stationary distributions
- Computable bounds for solutions to Poisson's equation and perturbation of Markov kernels
- Convergence speed and approximation accuracy of numerical MCMC
- On the approximation of one Markov chain by another
This page was built for publication: Approximations of geometrically ergodic reversible Markov chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5013245)
