The Annals of Applied Probability

Establishing some order amongst exact approximations of MCMCs

Christophe Andrieu and Matti Vihola

Full-text: Access denied (no subscription detected)

We're sorry, but we are unable to provide you with the full text of this article because we are not able to identify you as a subscriber. If you have a personal subscription to this journal, then please login. If you are already logged in, then you may need to update your profile to register your subscription. Read more about accessing full-text


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.

Article information

Ann. Appl. Probab., Volume 26, Number 5 (2016), 2661-2696.

Received: August 2014
Revised: October 2015
First available in Project Euclid: 19 October 2016

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 60J22: Computational methods in Markov chains [See also 65C40]
Secondary: 60J05: Discrete-time Markov processes on general state spaces 60E15: Inequalities; stochastic orderings 65C05: Monte Carlo methods

Asymptotic variance convex order Markov chain Monte Carlo martingale coupling pseudo-marginal algorithm


Andrieu, Christophe; Vihola, Matti. Establishing some order amongst exact approximations of MCMCs. Ann. Appl. Probab. 26 (2016), no. 5, 2661--2696. doi:10.1214/15-AAP1158.

Export citation


  • [1] Andrieu, C., Doucet, A. and Holenstein, R. (2010). Particle Markov chain Monte Carlo methods. J. R. Stat. Soc. Ser. B Stat. Methodol. 72 269–342.
  • [2] Andrieu, C. and Robert, C. P. (2001). Controlled MCMC for optimal sampling. Technical Report No. Ceremade 0125, Univ. Paris Dauphine.
  • [3] Andrieu, C. and Roberts, G. O. (2009). The pseudo-marginal approach for efficient Monte Carlo computations. Ann. Statist. 37 697–725.
  • [4] Andrieu, C. and Vihola, M. (2015). Convergence properties of pseudo-marginal Markov chain Monte Carlo algorithms. Ann. Appl. Probab. 25 1030–1077.
  • [5] Beaumont, M. A. (2003). Estimation of population growth or decline in genetically monitored populations. Genetics 164 1139–1160.
  • [6] Beaumont, M. A., Zhang, W. and Balding, D. J. (2002). Approximate Bayesian computation in population genetics. Genetics 162 2025–2035.
  • [7] Bellman, R. (1968). Some inequalities for the square root of a positive definite matrix. Linear Algebra Appl. 1 321–324.
  • [8] Beskos, A., Papaspiliopoulos, O., Roberts, G. O. and Fearnhead, P. (2006). Exact and computationally efficient likelihood-based estimation for discretely observed diffusion processes. J. R. Stat. Soc. Ser. B Stat. Methodol. 68 333–382.
  • [9] Bornn, L., Pillai, N., Smith, A. and Woodard, D. (2015). The use of a single pseudo-sample in approximate Bayesian computation. Preprint. Available at arXiv:1404.6298v4.
  • [10] Caracciolo, S., Pelissetto, A. and Sokal, A. D. (1990). Nonlocal Monte Carlo algorithm for self-avoiding walks with fixed endpoints. J. Stat. Phys. 60 1–53.
  • [11] Ceperley, D. M. and Dewing, M. (1999). The penalty method for random walks with uncertain energies. J. Chem. Phys. 110 9812.
  • [12] De Vylder, F. and Goovaerts, M. J. (1982). Analytical best upper bounds on stop-loss premiums. Insurance Math. Econom. 1 197–211.
  • [13] Dhaene, J. and Goovaerts, M. J. (1996). Dependency of risks and stop-loss order. Astin Bull. 26 201–212.
  • [14] Douc, R., Fort, G., Moulines, E. and Soulier, P. (2004). Practical drift conditions for subgeometric rates of convergence. Ann. Appl. Probab. 14 1353–1377.
  • [15] Doucet, A., Pitt, M. K., Deligiannidis, G. and Kohn, R. (2015). Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator. Biometrika 102 295–313.
  • [16] Drovandi, C. C. (2014). Pseudo-marginal algorithms with multiple CPUs. Working Paper No. 61505. Queensland Univ. Technology, Brisbane.
  • [17] Fearnhead, P. and Prangle, D. (2012). Constructing summary statistics for approximate Bayesian computation: Semi-automatic approximate Bayesian computation. J. R. Stat. Soc. Ser. B. Stat. Methodol. 74 419–474.
  • [18] Gilks, W. R., Roberts, G. O. and Sahu, S. K. (1998). Adaptive Markov chain Monte Carlo through regeneration. J. Amer. Statist. Assoc. 93 1045–1054.
  • [19] Goldstein, L., Rinott, Y. and Scarsini, M. (2011). Stochastic comparisons of stratified sampling techniques for some Monte Carlo estimators. Bernoulli 17 592–608.
  • [20] Goldstein, L., Rinott, Y. and Scarsini, M. (2012). Stochastic comparisons of symmetric sampling designs. Methodol. Comput. Appl. Probab. 14 407–420.
  • [21] Hoeffding, W. (1956). On the distribution of the number of successes in independent trials. Ann. Math. Statist. 27 713–721.
  • [22] Hürlimann, W. (2008). Extremal moment methods and stochastic orders: Application in actuarial science. Chapters IV, V and VI. Bol. Asoc. Mat. Venez. 15 153–301.
  • [23] Janssens, G. K. and Ramaekers, K. M. (2008). On the use of bounds on the stop-loss premium for an inventory management decision problem. J. Interdiscip. Math. 11 115–126.
  • [24] Jarner, S. F. and Hansen, E. (2000). Geometric ergodicity of Metropolis algorithms. Stochastic Process. Appl. 85 341–361.
  • [25] Jarner, S. F. and Roberts, G. O. (2002). Polynomial convergence rates of Markov chains. Ann. Appl. Probab. 12 224–247.
  • [26] Jones, G. L. (2004). On the Markov chain central limit theorem. Probab. Surv. 1 299–320.
  • [27] Karagiannis, G. and Andrieu, C. (2013). Annealed importance sampling reversible jump MCMC algorithms. J. Comput. Graph. Statist. 22 623–648.
  • [28] Karlin, S. and Novikoff, A. (1963). Generalized convex inequalities. Pacific J. Math. 13 1251–1279.
  • [29] Łatuszyński, K., Miasojedow, B. and Niemiro, W. (2013). Nonasymptotic bounds on the estimation error of MCMC algorithms. Bernoulli 19 2033–2066.
  • [30] Leisen, F. and Mira, A. (2008). An extension of Peskun and Tierney orderings to continuous time Markov chains. Statist. Sinica 18 1641–1651.
  • [31] Leskelä, L. and Vihola, M. (2014). Conditional convex orders and measurable martingale couplings. Preprint. Available at arXiv:1404.0999v3.
  • [32] Maire, F., Douc, R. and Olsson, J. (2014). Comparison of asymptotic variances of inhomogeneous Markov chains with application to Markov chain Monte Carlo methods. Ann. Statist. 42 1483–1510.
  • [33] Marjoram, P., Molitor, J., Plagnol, V. and Tavaré, S. (2003). Markov chain Monte Carlo without likelihoods. Proc. Natl. Acad. Sci. USA 100 15324–15328.
  • [34] Marshall, A. W., Olkin, I. and Arnold, B. (2010). Inequalities: Theory of Majorization and Its Applications. Springer, Berlin.
  • [35] Müller, A. and Stoyan, D. (2002). Comparison Methods for Stochastic Models and Risks. Wiley, Chichester.
  • [36] Nicholls, G. K., Fox, C. and Watt, A. M. (2012). Coupled MCMC with a randomized acceptance probability. Preprint. Available at arXiv:1205.6857v1.
  • [37] Peskun, P. H. (1973). Optimum Monte-Carlo sampling using Markov chains. Biometrika 60 607–612.
  • [38] Roberts, G. O. and Rosenthal, J. S. (1997). Geometric ergodicity and hybrid Markov chains. Electron. Commun. Probab. 2 13–25 (electronic).
  • [39] Roberts, G. O. and Tweedie, R. L. (2001). Geometric $L^{2}$ and $L^{1}$ convergence are equivalent for reversible Markov chains. J. Appl. Probab. 38A 37–41.
  • [40] Rudolf, D. (2012). Explicit error bounds for Markov chain Monte Carlo. Dissertationes Math. (Rozprawy Mat.) 485 1–93.
  • [41] Shaked, M. and Shanthikumar, J. G. (2007). Stochastic Orders. Springer, New York.
  • [42] Sherlock, C., Thiery, A. H., Roberts, G. O. and Rosenthal, J. S. (2015). On the efficiency of pseudo-marginal random walk Metropolis algorithms. Ann. Statist. 43 238–275.
  • [43] Solonen, A., Ollinaho, P., Laine, M., Haario, H., Tamminen, J. and Järvinen, H. (2012). Efficient MCMC for climate model parameter estimation: Parallel adaptive chains and early rejection. Bayesian Anal. 7 715–736.
  • [44] Strassen, V. (1965). The existence of probability measures with given marginals. Ann. Math. Statist. 36 423–439.
  • [45] Tavare, S., Balding, D. J., Griffiths, R. C. and Donnelly, P. (1997). Inferring coalescence times from DNA sequence data. Genetics 145 505–518.
  • [46] Tierney, L. (1998). A note on Metropolis–Hastings kernels for general state spaces. Ann. Appl. Probab. 8 1–9.
  • [47] Tuominen, P. and Tweedie, R. L. (1994). Subgeometric rates of convergence of $f$-ergodic Markov chains. Adv. in Appl. Probab. 26 775–798.