Abstract
Particle filters are a powerful and flexible tool for performing inference on state-space models. They involve a collection of samples evolving over time through a combination of sampling and re-sampling steps. The re-sampling step is necessary to ensure that weight degeneracy is avoided. In several situations of statistical interest, it is important to be able to compare the estimates produced by two different particle filters; consequently, being able to efficiently couple two particle filter trajectories is often of paramount importance. In this text, we propose several ways to do so. In particular, we leverage ideas from the optimal transportation literature. In general, though computing the optimal transport map is extremely computationally expensive, to deal with this, we introduce computationally tractable approximations to optimal transport couplings. We demonstrate that our resulting algorithms for coupling two particle filter trajectories often perform orders of magnitude more efficiently than more standard approaches.
Similar content being viewed by others
References
Alquier, P., Friel, N., Everitt, R., Boland, A.: Noisy monte carlo: Convergence of markov chains with approximate transition kernels. Stat. Comput. 26(1–2), 29–47 (2016)
Andrieu, C., Roberts, G.O.: The pseudo-marginal approach for efficient monte carlo computations. Ann. Stat. 37(2), 697–725 (2009)
Andrieu, C., Vihola, M.: Establishing some order amongst exact approximations of mcmcs. arXiv preprint arXiv:1404.6909 (2014)
Andrieu, C., Doucet, A., Holenstein, R.: Particle markov chain monte carlo methods. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 72(3), 269–342 (2010)
Andrieu, C., Vihola, M., et al.: Convergence properties of pseudo-marginal markov chain monte carlo algorithms. Ann. Appl. Probab. 25(2), 1030–1077 (2015)
Beskos, A., Jasra, A., Law, K., Tempone, R., Zhou, Y.: Multilevel sequential monte carlo samplers. arXiv preprint arXiv:1503.07259 (2015)
Cappé, O., Moulines, E., Rydén, T.: Inference in hidden markov models. Springer, New York (2009)
Chopin, N., Singh, S.S., et al.: On particle gibbs sampling. Bernoulli 21(3), 1855–1883 (2015)
Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, pp. 2292–2300 (2013)
Dantzig, G.B.: Linear Programming and Extensions. Princeton university press, Princeton (1998)
Del Moral, P., Jasra, A., Law, K., Zhou, Y.: Multilevel sequential monte carlo samplers for normalizing constants. arXiv preprint arXiv:1603.01136 (2016)
Deligiannidis, G., Doucet, A., Pitt, M.K., Kohn, R.: The correlated pseudo-marginal method. arXiv preprint arXiv:1511.04992 (2015)
Deming, W.E., Stephan, F.F.: On a least squares adjustment of a sampled frequency table when the expected marginal totals are known. Ann. Math. Stat. 11(4), 427–444 (1940)
Doucet, A., Johansen, A.M.: A tutorial on particle filtering and smoothing: fifteen years later. Handb. Nonlinear Filter. 12(656–704), 3 (2009)
Doucet, A., Pitt, M., Deligiannidis, G., Kohn, R.: Efficient implementation of markov chain monte carlo when using an unbiased likelihood estimator. Biometrika 102(2), 295–313 (2015)
Durbin, J., Koopman, S.J.: Time Series Analysis by State Space Methods, vol. 38. Oxford University Press, Oxford (2012)
Érdi, P., Lente, G.: Stochastic chemical kinetics. Theory (Mostly) Syst. Biol. Appl. (2014)
Ferradans, S., Papadakis, N., Peyré, G., Aujol, J.F.: Regularized discrete optimal transport. SIAM J. Imaging Sci. 7(3), 1853–1882 (2014)
Franzke, B., Kosko, B.: Using noise to speed up markov chain monte carlo estimation. Proced. Comput. Sci. 53, 113–120 (2015)
Friedman, J.H., Bentley, J.L., Finkel, R.A.: An algorithm for finding best matches in logarithmic expected time. ACM Trans. Math. Softw. (TOMS) 3(3), 209–226 (1977)
Geyer, C.J.: Practical markov chain monte carlo. Stat. Sci. 7, 473–483 (1992)
Giles, M.B.: Multilevel monte carlo path simulation. Oper. Res. 56(3), 607–617 (2008)
Giles, M.B.: Multilevel monte carlo methods. Acta Numer. 24, 259–328 (2015)
Gillespie, D.T.: Stochastic simulation of chemical kinetics. Ann. Rev. Phys. Chem. 58, 35–55 (2007)
Golightly, A., Wilkinson, D.J.: Bayesian parameter inference for stochastic biochemical network models using particle markov chain monte carlo. Interface focus 1(6), 807–820 (2011)
Gordon, N.J., Salmond, D.J., Smith, A.F.: Novel approach to nonlinear/non-gaussian bayesian state estimation. IET 140, 107–113 (1993)
Gregory, A., Cotter, C., Reich, S.: Multilevel ensemble transform particle filtering. SIAM J. Sci. Comput. 38(3), A1317–A1338 (2016)
Harrison, J., West, M.: Bayesian Forecasting & Dynamic Models. Springer, Berlin (1999)
Hoel, H., Law, K.J., Tempone, R.: Multilevel ensemble kalman filtering. arXiv preprint arXiv:1502.06069 (2015)
Ingle, A.N., Ma, C., Varghese, T.: Ultrasonic tracking of shear waves using a particle filter. Med. Phys. 42(11), 6711–6724 (2015)
Ionides, E.L., Bhadra, A., Atchadé, Y., King, A., et al.: Iterated filtering. Ann. Stat. 39(3), 1776–1802 (2011)
Jacob, P.E., Lindsten, F., Schön, T.B.: Coupling of particle filters. arXiv preprint arXiv:1606.01156 (2016)
Jasra, A., Kamatani, K., Law, K.J., Zhou, Y.: Multilevel particle filter. arXiv preprint arXiv:1510.04977 (2015)
Jasra, A., Kamatani, K., Osei, P.P., Zhou, Y.: Multilevel particle filters: Normalizing constant estimation. arXiv preprint arXiv:1605.04963 (2016)
Johannes, M.S., Polson, N.G., Stroud, J.R.: Optimal filtering of jump diffusions: extracting latent states from asset prices. Rev. Financ. Stud. 22(7), 2759–2799 (2009)
Kantas, N., Doucet, A., Singh, S.S., Maciejowski, J., Chopin, N., et al.: On particle methods for parameter estimation in state-space models. Stat. Sci. 30(3), 328–351 (2015)
Kantorovitch, L.: On the translocation of masses. Manag. Sci. 5(1), 1–4 (1958)
King, A.A., Ionides, E.L., Pascual, M., Bouma, M.J.: Inapparent infections and cholera dynamics. Nature 454(7206), 877–880 (2008)
Kitagawa, G.: Monte carlo filter and smoother for non-gaussian nonlinear state space models. J. Comput. Gr. Stat. 5(1), 1–25 (1996)
Knight, P.A.: The sinkhorn-knopp algorithm: convergence and applications. SIAM J. Matrix Anal. Appl. 30(1), 261–275 (2008)
Kong, A., Liu, J.S., Wong, W.H.: Sequential imputations and bayesian missing data problems. J. Am. Stat. Assoc. 89(425), 278–288 (1994)
Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1–2), 83–97 (1955)
Mahalanobis, P.C.: On the generalized distance in statistics. Proc. Natl. Inst. Sci. (Calcutta) 2, 49–55 (1936)
Medina-Aguayo, F.J., Lee, A., Roberts, G.O.: Stability of noisy metropolis–hastings. Stat. Comput. pp 1–25 (2015)
Naidan, B., Boytsov, L., Nyberg, E.: Permutation search methods are efficient, yet faster search is possible. Proc. VLDB Endow. 8(12), 1618–1629 (2015)
Nemeth, C., Fearnhead, P., Mihaylova, L.: Sequential monte carlo methods for state and parameter estimation in abruptly changing environments. IEEE Trans. Signal Process. 62(5), 1245–1255 (2014)
Newman, K.B., Fernández, C., Thomas, L., Buckland, S.T.: Monte carlo inference for state-space models of wild animal populations. Biometrics 65(2), 572–583 (2009)
O’Neill, P.D., Balding, D.J., Becker, N.G., Eerola, M., Mollison, D.: Analyses of infectious disease data from household outbreaks by markov chain monte carlo methods. J. R. Stat. Soc. Ser. C (Appl. Stat.) 49(4), 517–542 (2000)
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Lear. Res. 12, 2825–2830 (2011)
Pele, O., Werman, M.: Fast and robust earth mover’s distances. In: Computer Vision, 2009 IEEE 12th International Conference on, IEEE, pp 460–467 (2009)
Poyiadjis, G., Doucet, A., Singh, S.S.: Particle approximations of the score and observed information matrix in state space models with application to parameter estimation. Biometrika 98(1), 65–80 (2011)
Reich, S.: A guided sequential monte carlo method for the assimilation of data into stochastic dynamical systems. In: Recent Trends in Dynamical Systems, Springer, pp 205–220 (2013a)
Reich, S.: A nonparametric ensemble transform method for bayesian inference. SIAM J. Sci. Comput. 35(4), A2013–A2024 (2013b)
Ross, S.M., Peköz, E.A.: A second course in probability.www.ProbabilityBookstore.com (2007)
Schmitzer, B.: A sparse multi-scale algorithm for dense optimal transport. arXiv preprint arXiv:1510.05466 (2015)
Sherlock, C., Thiery, A.H., Roberts, G.O., Rosenthal, J.S., et al.: On the efficiency of pseudo-marginal random walk metropolis algorithms. Ann. Stat. 43(1), 238–275 (2015)
Slaney, M., Casey, M.: Locality-sensitive hashing for finding nearest neighbors [lecture notes]. IEEE Signal Process. Mag. 25(2), 128–131 (2008)
Soules, G.W.: The rate of convergence of sinkhorn balancing. Linear Algebra Appl. 150, 3–40 (1991)
Sutharsan, S., Kirubarajan, T., Lang, T., McDonald, M.: An optimization-based parallel particle filter for multitarget tracking. IEEE Trans. Aerosp. Electr. Syst. 48(2), 1601–1618 (2012)
Toral, R., Mirasso, C.R., Hernández-Garcıa, E., Piro, O.: Analytical and numerical studies of noise-induced synchronization of chaotic systems. Chaos: an Interdisciplinary. J. Nonlinear Sci. 11(3), 665–673 (2001)
Trigila, G., Tabak, E.G.: Data-driven optimal transport. Commun. Pure and Appl. Math. 3, 45 (2015)
Wald, I., Havran, V.: On building fast kd-trees for ray tracing, and on doing that in o (n log n). In: Interactive Ray Tracing 2006, IEEE Symposium on, IEEE, pp. 61–69 (2006)
Wei, Z., Tao, T., ZhuoShu, D., Zio, E.: A dynamic particle filter-support vector regression method for reliability prediction. Reliab. Eng. Syst.Saf. 119, 109–116 (2013)
Wood, S.N.: Statistical inference for noisy nonlinear ecological dynamic systems. Nature 466(7310), 1102–1104 (2010)
Yin, S., Zhu, X.: Intelligent particle filter and its application to fault detection of nonlinear system. IEEE Trans. Ind. Electr. 62(6), 3852–3861 (2015)
Zhou, C., Kurths, J.: Noise-induced phase synchronization and synchronization transitions in chaotic oscillators. Phys. Rev. Lett. 88(23), 230,602 (2002)
Acknowledgements
We would like to thank two anonymous reviewers for their constructive comments. A. Jasra is also affiliated with the RMI, CQF and OR and Analytics cluster at NUS. Ministry of Education—Singapore (AcRF R-155-000-150-133, AcRF R-155-000-156-112).
Author information
Authors and Affiliations
Corresponding author
Additional information
Ajay Jasra was funded by AcRF tier 1 Grant R-155-000-156-112. Alexandre H Thiery was funded by AcRF Grant R-155-000-150-133.
Rights and permissions
About this article
Cite this article
Sen, D., Thiery, A.H. & Jasra, A. On coupling particle filter trajectories. Stat Comput 28, 461–475 (2018). https://doi.org/10.1007/s11222-017-9740-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-017-9740-z