- JYX front page
- →
- Articles
- →
- Faculty of Mathematics and Science
- →
- View Item

JavaScript is disabled for your browser. Some features of this site may not work without it.

Citation:

Andrieu, C., & Vihola, M. (2016). Establishing some order amongst exact approximations of MCMCs. *Annals of Applied Probability*, 26 (5), 2661-2696. doi:10.1214/15-AAP1158

Title: | Establishing some order amongst exact approximations of MCMCs |

Author: | Andrieu, Christophe; Vihola, Matti |

Abstract: | Exact approximations of Markov chain Monte Carlo (MCMC) algorithms are a general emerging class of sampling algorithms. One of the main ideas behind exact approximations consists of replacing intractable quantities required to run standard MCMC algorithms, such as the target probability density in a Metropolis–Hastings algorithm, with estimators. Perhaps surprisingly, such approximations lead to powerful algorithms which are exact in the sense that they are guaranteed to have correct limiting distributions. In this paper, we discover a general framework which allows one to compare, or order, performance measures of two implementations of such algorithms. In particular, we establish an order with respect to the mean acceptance probability, the first autocorrelation coefficient, the asymptotic variance and the right spectral gap. The key notion to guarantee the ordering is that of the convex order between estimators used to implement the algorithms. We believe that our convex order condition is close to optimal, and this is supported by a counterexample which shows that a weaker variance order is not sufficient. The convex order plays a central role by allowing us to construct a martingale coupling which enables the comparison of performance measures of Markov chain with differing invariant distributions, contrary to existing results. We detail applications of our result by identifying extremal distributions within given classes of approximations, by showing that averaging replicas improves performance in a monotonic fashion and that stratification is guaranteed to improve performance for the standard implementation of the Approximate Bayesian Computation (ABC) MCMC method. ... |

Publisher: | Institute of Mathematical Statistics |

Date: | 2016 |

Belongs to series: | Annals of Applied Probability |

ISSN: | 1050-5164 Search the Publication Forum |

Subjects: | Markov chain Monte Carlo algorithms mathematics |

Rights: | © Institute of Mathematical Statistics, 2016. Published in this repository with the kind permission of the publisher. |

DOI: | 10.1214/15-AAP1158 |

Permanent link to this item: http://urn.fi/URN:NBN:fi:jyu-201610254431

- Can the adaptive Metropolis algorithm collapse without the covariance lower bound? (2011)
- Cluster priors in the Bayesian modelling of fMRI data (2001)
- Statistical analysis of β decays and the effective value of gA in the proton-neutron quasiparticle random-phase approximation framework (2016)
- Value at risk -laskennan soveltuvuus lentoyhtiölle : case: Finnair oyj (2001)
- Latent growth mixture modeling : a simulation study (2007)

- Uniform ergodicity of the iterated conditional SMC and geometric ergodicity of particle Gibbs samplers (2018)
- Can the adaptive Metropolis algorithm collapse without the covariance lower bound? (2011)
- On the convergence of unconstrained adaptive Markov chain Monte Carlo algorithms (2010)
- Conditional convex orders and measurable martingale couplings (2017)
- Generalized dimension distortion under Sobolev mappings (2011)