The Annals of Statistics

Exponential ergodicity of the bouncy particle sampler

George Deligiannidis, Alexandre Bouchard-Côté, and Arnaud Doucet

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


Nonreversible Markov chain Monte Carlo schemes based on piecewise deterministic Markov processes have been recently introduced in applied probability, automatic control, physics and statistics. Although these algorithms demonstrate experimentally good performance and are accordingly increasingly used in a wide range of applications, geometric ergodicity results for such schemes have only been established so far under very restrictive assumptions. We give here verifiable conditions on the target distribution under which the Bouncy Particle Sampler algorithm introduced in [Phys. Rev. E 85 (2012) 026703, 1671–1691] is geometrically ergodic and we provide a central limit theorem for the associated ergodic averages. This holds essentially whenever the target satisfies a curvature condition and the growth of the negative logarithm of the target is at least linear and at most quadratic. For target distributions with thinner tails, we propose an original modification of this scheme that is geometrically ergodic. For targets with thicker tails, we extend the idea pioneered in [Ann. Statist. 40 (2012) 3050–3076] in a random walk Metropolis context. We establish geometric ergodicity of the Bouncy Particle Sampler with respect to an appropriate transformation of the target. Mapping the resulting process back to the original parameterization, we obtain a geometrically ergodic piecewise deterministic Markov process.

Article information

Ann. Statist., Volume 47, Number 3 (2019), 1268-1287.

Received: August 2017
Revised: April 2018
First available in Project Euclid: 13 February 2019

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Primary: 60J25: Continuous-time Markov processes on general state spaces 65C05: Monte Carlo methods 65C40: Computational Markov chains 60F05: Central limit and other weak theorems

Piecewise deterministic Markov process Markov chain Monte Carlo geometric ergodicity change of variable central limit theorem


Deligiannidis, George; Bouchard-Côté, Alexandre; Doucet, Arnaud. Exponential ergodicity of the bouncy particle sampler. Ann. Statist. 47 (2019), no. 3, 1268--1287. doi:10.1214/18-AOS1714.

Export citation


  • [1] Bierkens, J., Bouchard-Côté, A., Doucet, A., Duncan, A. B., Fearnhead, P., Lienart, T., Roberts, G. O. and Vollmer, S. J. (2018). Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains. Statist. Probab. Lett. 136 148–154.
  • [2] Bierkens, J. and Duncan, A. (2017). Limit theorems for the zig-zag process. Adv. in Appl. Probab. 49 791–825.
  • [3] Bierkens, J., Fearnhead, P. and Roberts, G. O. (2016). The Zig-Zag process and super-efficient sampling for Bayesian analysis of big data. Available at arXiv:1607.03188.
  • [4] Bierkens, J. and Roberts, G. (2017). A piecewise deterministic scaling limit of lifted Metropolis–Hastings in the Curie–Weiss model. Ann. Appl. Probab. 27 846–882.
  • [5] Bierkens, J., Roberts, G. O. and Zitt, P. A. (2017). Ergodicity of the Zig-Zag process. Available at arXiv:1712.09875.
  • [6] Bouchard-Côté, A., Vollmer, S. J. and Doucet, A. (2018). The bouncy particle sampler: A non-reversible rejection-free Markov chain Monte Carlo method. J. Amer. Statist. Assoc. DOI:10.1080/01621459.2017.1294075. Available at arXiv:1510.02451.
  • [7] Burke, C. J. and Rosenblatt, M. (1958). A Markovian function of a Markov chain. Ann. Math. Stat. 29 1112–1122.
  • [8] Costa, O. L. V. (1990). Stationary distributions for piecewise-deterministic Markov processes. J. Appl. Probab. 27 60–73.
  • [9] Costa, O. L. V. and Dufour, F. (2008). Stability and ergodicity of piecewise deterministic Markov processes. SIAM J. Control Optim. 47 1053–1077.
  • [10] Davis, M. H. A. (1984). Piecewise-deterministic Markov processes: A general class of nondiffusion stochastic models. J. Roy. Statist. Soc. Ser. B 46 353–388.
  • [11] Davis, M. H. A. (1993). Markov Models and Optimization. Monographs on Statistics and Applied Probability 49. Chapman & Hall, London.
  • [12] Del Moral, P. and Penev, S. (2017). Stochastic Processes: From Applications to Theory. CRC Press, Boca Raton, FL.
  • [13] Deligiannidis, G., Bouchard-Côté, A. and Doucet, A. (2019). Supplement to “Exponential ergodicity of the bouncy particle sampler.” DOI:10.1214/18-AOS1714SUPP.
  • [14] Devroye, L. (1986). Nonuniform Random Variate Generation. Springer, New York.
  • [15] Down, D., Meyn, S. P. and Tweedie, R. L. (1995). Exponential and uniform ergodicity of Markov processes. Ann. Probab. 23 1671–1691.
  • [16] Fearnhead, P., Bierkens, J., Pollock, M. and Roberts, G. O. (2016). Piecewise deterministic Markov processes for continuous-time Monte Carlo. Available at arXiv:1611.07873.
  • [17] Fétique, N. (2017). Long-time behaviour of generalised Zig-Zag process. Available at arXiv:1710.01087.
  • [18] Fontbona, J., Guérin, H. and Malrieu, F. (2016). Long time behavior of telegraph processes under convex potentials. Stochastic Process. Appl. 126 3077–3101.
  • [19] Glynn, P. W. and Meyn, S. P. (1996). A Liapounov bound for solutions of the Poisson equation. Ann. Probab. 24 916–931.
  • [20] Gramacy, R. B. and Polson, N. G. (2012). Simulation-based regularized logistic regression. Bayesian Anal. 7 567–589.
  • [21] Isobe, M. and Krauth, W. (2015). Hard-sphere melting and crystallization with event-chain Monte Carlo. J. Chem. Phys. 143 084509.
  • [22] Jarner, S. F. and Hansen, E. (2000). Geometric ergodicity of Metropolis algorithms. Stochastic Process. Appl. 85 341–361.
  • [23] Jarner, S. F. and Tweedie, R. L. (2003). Necessary conditions for geometric and polynomial ergodicity of random-walk-type Markov chains. Bernoulli 9 559–578.
  • [24] Johnson, L. T. and Geyer, C. J. (2012). Variable transformation to obtain geometric ergodicity in the random-walk Metropolis algorithm. Ann. Statist. 40 3050–3076.
  • [25] Jones, G. L. and Hobert, J. P. (2001). Honest exploration of intractable probability distributions via Markov chain Monte Carlo. Statist. Sci. 16 312–334.
  • [26] Kapfer, S. C. and Krauth, W. (2016). Cell-veto Monte Carlo algorithms for long-range systems. Phys. Rev. E 94 3 031302(R).
  • [27] Livingstone, S., Betancourt, M., Byrne, S. and Girolami, M. (2016). On the geometric ergodicity of Hamiltonian Monte Carlo. Available at arXiv:1601.08057.
  • [28] Mesquita, A. R. and Hespanha, J. P. (2010). Construction of Lyapunov functions for piecewise-deterministic Markov processes. In Proc. 49th IEEE Conf. Decision and Control 2408–2413.
  • [29] Mesquita, A. R. and Hespanha, J. P. (2012). Jump control of probability densities with applications to autonomous vehicle motion. IEEE Trans. Automat. Control 57 2588–2598.
  • [30] Meyn, S. P. and Tweedie, R. L. (1993). Stability of Markovian processes. III. Foster–Lyapunov criteria for continuous-time processes. Adv. in Appl. Probab. 25 518–548.
  • [31] Michel, M., Kapfer, S. C. and Krauth, W. (2014). Generalized event-chain Monte Carlo: Constructing rejection-free global-balance algorithms from infinitesimal steps. J. Chem. Phys. 140 054116.
  • [32] Monmarché, P. (2016). Piecewise deterministic simulated annealing. ALEA Lat. Am. J. Probab. Math. Stat. 13 357–398.
  • [33] Neal, R. M. (2003). Slice sampling. Ann. Statist. 31 705–767.
  • [34] Nishikawa, Y. and Hukushima, K. (2016). Event-chain Monte Carlo algorithm for continuous spin systems and its application. Inst. Phys. Conf. Ser. 750 012014.
  • [35] Pakman, A., Gilboa, D., Carlson, D. and Paninski, L. (2017). Stochastic bouncy particle sampler. In Proc. 34th Int. Conf. Machine Learning 2741–2750.
  • [36] Peters, E. A. J. F. and de With, G. (2012). Rejection-free Monte Carlo sampling for general potentials. Phys. Rev. E 85 026703, 1671–1691.
  • [37] Roberts, G. O. and Rosenthal, J. S. (1996). Quantitative bounds for convergence rates of continuous time Markov processes. Electron. J. Probab. 1 no. 9, approx. 21 pp.
  • [38] Roberts, G. O. and Tweedie, R. L. (1996). Exponential convergence of Langevin distributions and their discrete approximations. Bernoulli 2 341–363.
  • [39] Roberts, G. O. and Tweedie, R. L. (1996). Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms. Biometrika 83 95–110.
  • [40] Sherlock, C. and Thiery, A. (2017). A discrete bouncy particle sampler. Available at arXiv:1707.05200.
  • [41] Vanetti, P., Bouchard-Côté, A., Deligiannidis, G. and Doucet, A. (2017). Piecewise deterministic Markov chain Monte Carlo. Available at arXiv:1707.05296.
  • [42] Wu, C. and Robert, C. P. (2017). Generalized bouncy particle sampler. Available at arXiv:1706.04781.

Supplemental materials

  • Supplement to “Exponential ergodicity of the bouncy particle sampler”. We provide detailed proofs of all results given in the main paper.