Almost sure convergence rates of adaptive increasingly rare Markov chain Monte Carlo
arXiv:2402.12122 · doi:10.1016/j.spa.2026.104905
Abstract
We consider adaptive increasingly rare Markov chain Monte Carlo (MCMC) algorithms, which are adaptive MCMC methods, where the adaptation concerning the "past'' happens less and less frequently over time. Under a contraction assumption with respect to a Wasserstein-like function we deduce upper bounds of the convergence rate of Monte Carlo sums taking a renormalisation factor into account that is "almost'' the one that appears in a law of the iterated logarithm. We demonstrate the applicability of our results by considering different settings, among which are those of simultaneous geometric and uniform ergodicity. All proofs are carried out on an augmented state space, including the classical non-augmented setting as a special case. In contrast to other adaptive MCMC limit theory, some technical assumptions, like diminishing adaptation, are not needed.
References in corpus (10)
- On the ergodicity properties of some adaptive MCMC algorithms
- Renewal theory and computable convergence rates for geometrically ergodic Markov chains
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Explicit error bounds for Markov chain Monte Carlo
- On a generalization of the preconditioned Crank-Nicolson Metropolis algorithm
- On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
- Proposals which speed-up function-space MCMC
- Nonasymptotic bounds on the estimation error of MCMC algorithms