On the stability and ergodicity of adaptive scaling Metropolis algorithms
arXiv:0903.4061 · doi:10.1016/j.spa.2011.08.006
Abstract
The stability and ergodicity properties of two adaptive random walk Metropolis algorithms are considered. The both algorithms adjust the scaling of the proposal distribution continuously based on the observed acceptance probability. Unlike the previously proposed forms of the algorithms, the adapted scaling parameter is not constrained within a predefined compact interval. The first algorithm is based on scale adaptation only, while the second one incorporates also covariance adaptation. A strong law of large numbers is shown to hold assuming that the target density is smooth enough and has either compact support or super-exponentially decaying tails.
24 pages, 1 figure; major revision
References in corpus (3)
Cited by in corpus (15)
- A Survey of Monte Carlo Methods for Parameter Estimation
- Adaptive Gibbs samplers and related MCMC methods
- A consistent analysis of three years of ground- and space-based photometry of TrES-2
- Markovian stochastic approximation with expanding projections
- Grapham: Graphical Models with Adaptive Random Walk Metropolis Algorithms
- Adaptive parallel tempering algorithm
- On the stability of some controlled Markov chains and its applications to stochastic approximation with Markovian dynamic
- Adaptive Gibbs samplers
- Finite Sample Properties of Adaptive Markov Chains via Curvature
- Adapting The Gibbs Sampler
- Can the Adaptive Metropolis Algorithm Collapse Without the Covariance Lower Bound?
- Adaptive Metropolis Algorithm Using Variational Bayesian Adaptive Kalman Filter
- Robust adaptive Metropolis algorithm with coerced acceptance rate
- Bayesian Inference of Reproduction Number from Epidemiological and Genetic Data Using Particle MCMC
- Air Markov Chain Monte Carlo