Abstract
The Dobrushin comparison theorem is a powerful tool to bound the difference between the marginals of high-dimensional probability distributions in terms of their local specifications. Originally introduced to prove uniqueness and decay of correlations of Gibbs measures, it has been widely used in statistical mechanics as well as in the analysis of algorithms on random fields and interacting Markov chains. However, the classical comparison theorem requires validity of the Dobrushin uniqueness criterion, essentially restricting its applicability in most models to a small subset of the natural parameter space. In this paper we develop generalized Dobrushin comparison theorems in terms of influences between blocks of sites, in the spirit of Dobrushin–Shlosman and Weitz, that substantially extend the range of applicability of the classical comparison theorem. Our proofs are based on the analysis of an associated family of Markov chains. We develop in detail an application of our main results to the analysis of sequential Monte Carlo algorithms for filtering in high dimension.
Similar content being viewed by others
References
Cappé, O., Moulines, E., Rydén, T.: Inference in Hidden Markov Models. Springer Series in Statistics. Springer, New York (2005)
Dai Pra, P., Scoppola, B., Scoppola, E.: Sampling from a Gibbs measure with pair interaction by means of PCA. J. Stat. Phys. 149(4), 722–737 (2012)
Del Moral, P., Guionnet, A.: On the stability of interacting processes with applications to filtering and genetic algorithms. Ann. Inst. H. Poincaré Probab. Stat. 37(2), 155–194 (2001)
Dobrushin, R.L., Shlosman, S.B.: Constructive criterion for the uniqueness of Gibbs field. In: Statistical physics and dynamical systems (Köszeg, 1984), Program Physics, vol. 10, pp. 347–370. Birkhäuser Boston, Boston (1985)
Dobrušin, R.L.: Definition of a system of random variables by means of conditional distributions. Teor. Verojatnost. i Primenen. 15, 469–497 (1970)
Dudley, R.M.: Real Analysis and Probability, Cambridge Studies in Advanced Mathematics, vol. 74. Cambridge University Press, Cambridge (2002) (Revised reprint of the 1989 original)
Dyer, M., Goldberg, L.A., Jerrum, M.: Dobrushin conditions and systematic scan. Comb. Probab. Comput. 17(6), 761–779 (2008)
Dyer, M., Goldberg, L.A., Jerrum, M.: Matrix norms and rapid mixing for spin systems. Ann. Appl. Probab. 19(1), 71–107 (2009)
Föllmer, H.: Tail structure of Markov chains on infinite product spaces. Z. Wahrsch. Verw. Gebiete 50(3), 273–285 (1979)
Föllmer, H.: A covariance estimate for Gibbs measures. J. Funct. Anal. 46(3), 387–395 (1982)
Föllmer, H.: Random fields and diffusion processes. In: École d’Été de Probabilités de Saint-Flour XV–XVII, 1985–1987, Lecture Notes in Mathematics, vol. 1362, pp. 101–203. Springer, Berlin (1988)
Georgii, H.O.: Measures and Phase Transitions, de Gruyter Studies in Mathematics, vol. 9, 2nd edn. Walter de Gruyter & Co., Berlin (2011)
Guionnet, A., Zegarlinski, B.: Lectures on Logarithmic Sobolev Inequalities. In: Séminaire de Probabilités, XXXVI, Lecture Notes in Mathematics, vol. 1801, pp. 1–134. Springer, Berlin (2003)
Kallenberg, O.: Foundations of Modern Probability. Probability and its Applications (New York), 2nd edn. Springer-Verlag, New York (2002)
Külske, C.: Concentration inequalities for functions of Gibbs fields with application to diffraction and random Gibbs measures. Commun. Math. Phys. 239(1–2), 29–51 (2003)
Lebowitz, J.L., Maes, C., Speer, E.R.: Statistical mechanics of probabilistic cellular automata. J. Stat. Phys. 59(1–2), 117–170 (1990)
Liggett, T.M.: Interacting Particle Systems. Classics in Mathematics. Springer-Verlag, Berlin (2005) (Reprint of the 1985 original)
Rebeschini, P., van Handel, R.: Can Local Particle Filters Beat the Curse of Dimensionality? Preprint arxiv:1301.6585 (2013)
Royden, H.L.: Real Analysis, 3rd edn. Macmillan Publishing Company, New York (1988)
Rue, T.D.L., Fernández, R., Sokal, A.D.: How to clean a dirty floor: probabilistic potential theory and the Dobrushin uniqueness theorem. Markov Process Relat. Fields 14(1), 1–78 (2008)
Simon, B.: The Statistical Mechanics of Lattice Gases. Princeton Series in Physics, vol. I. Princeton University Press, Princeton (1993)
Tatikonda, S.C.: Convergence of the sum-product algorithm. In: Information Theory Workshop, 2003. Proceedings. 2003 IEEE, pp. 222–225 (2003)
van der Vaart, A.W., Wellner, J.A.: Weak Convergence and Empirical Processes. Springer Series in Statistics. With Applications to Statistics. Springer-Verlag, New York (1996)
Villani, C.: Optimal Transport, Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences], vol. 338. Springer-Verlag, Berlin (2009). Old and new
Weitz, D.: Combinatorial criteria for uniqueness of Gibbs measures. Random Struct. Algorithms 27(4), 445–475 (2005)
Wu, L.: Poincaré and transportation inequalities for Gibbs measures under the Dobrushin uniqueness condition. Ann. Probab. 34(5), 1960–1989 (2006)
Younes, L.: Parametric inference for imperfectly observed Gibbsian fields. Probab. Theory Relat. Fields 82(4), 625–645 (1989)
Acknowledgments
This work was supported in part by NSF Grants DMS-1005575 and CAREER-DMS-1148711, and by the ARO through PECASE award W911NF-14-1-0094.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rebeschini, P., van Handel, R. Comparison Theorems for Gibbs Measures. J Stat Phys 157, 234–281 (2014). https://doi.org/10.1007/s10955-014-1087-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10955-014-1087-7