Approximations of Geometrically Ergodic Reversible Markov Chains
arXiv:1702.07441 · doi:10.1017/apr.2021.10
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.
References in corpus (13)
- MCMC using Hamiltonian dynamics
- General state space Markov chains and MCMC algorithms
- The pseudo-marginal approach for efficient Monte Carlo computations
- Renewal theory and computable convergence rates for geometrically ergodic Markov chains
- Coresets for Scalable Bayesian Logistic Regression
- On the Geometric Ergodicity of Hamiltonian Monte Carlo
- Explicit error bounds for Markov chain Monte Carlo
- Automated Scalable Bayesian Inference via Hilbert Coresets
- Ergodicity of Approximate MCMC Chains with Applications to Large Data Sets
- Approximating Markov chains and V-geometric ergodicity via weak perturbation theory
- Perturbation Bounds for Monte Carlo within Metropolis via Restricted Approximations
- Error bounds for Approximations of Markov chains used in Bayesian Sampling
- Coupling and Decoupling to bound an approximating Markov Chain
Cited by in corpus (6)
- Perturbation Bounds for Monte Carlo within Metropolis via Restricted Approximations
- Hoeffding's lemma for Markov Chains and its applications to statistical learning
- Pólya Urn Latent Dirichlet Allocation: a doubly sparse massively parallel sampler
- Importance sampling correction versus standard averages of reversible MCMCs in terms of the asymptotic variance
- Convergence Speed and Approximation Accuracy of Numerical MCMC
- Perturbation theory for killed Markov processes and quasi-stationary distributions