The Annals of Probability
- Ann. Probab.
- Volume 38, Number 6 (2010), 2418-2442.
Curvature, concentration and error estimates for Markov chain Monte Carlo
Aldéric Joulin and Yann Ollivier
Full-text: Open access
Abstract
We provide explicit nonasymptotic estimates for the rate of convergence of empirical means of Markov chains, together with a Gaussian or exponential control on the deviations of empirical means. These estimates hold under a “positive curvature” assumption expressing a kind of metric ergodicity, which generalizes the Ricci curvature from differential geometry and, on finite graphs, amounts to contraction under path coupling.
Article information
Source
Ann. Probab., Volume 38, Number 6 (2010), 2418-2442.
Dates
First available in Project Euclid: 24 September 2010
Permanent link to this document
https://projecteuclid.org/euclid.aop/1285334210
Digital Object Identifier
doi:10.1214/10-AOP541
Mathematical Reviews number (MathSciNet)
MR2683634
Zentralblatt MATH identifier
1207.65006
Subjects
Primary: 65C05: Monte Carlo methods 60J22: Computational methods in Markov chains [See also 65C40] 62E17: Approximations to distributions (nonasymptotic)
Keywords
Markov chain Monte Carlo concentration of measure Ricci curvature Wasserstein distance
Citation
Joulin, Aldéric; Ollivier, Yann. Curvature, concentration and error estimates for Markov chain Monte Carlo. Ann. Probab. 38 (2010), no. 6, 2418--2442. doi:10.1214/10-AOP541. https://projecteuclid.org/euclid.aop/1285334210
References
- [1] Bubley, R. and Dyer, M. E. (1997). Path coupling: A technique for proving rapid mixing in Markov chains. FOCS 223–231.
- [2] Bakry, D. and Émery, M. (1985). Diffusions hypercontractives. In Séminaire de Probabilités, XIX, 1983/84. Lecture Notes in Math. 1123 177–206. Springer, Berlin.Mathematical Reviews (MathSciNet): MR889476
Zentralblatt MATH: 0561.60080
Digital Object Identifier: doi:10.1007/BFb0075847 - [3] Bismut, J.-M. (1981). Mécanique Aléatoire. Lecture Notes in Math. 866. Springer, Berlin.Mathematical Reviews (MathSciNet): MR629977
- [4] Basak, G. K., Hu, I. and Wei, C.-Z. (1997). Weak convergence of recursions. Stochastic Process. Appl. 68 65–82.Mathematical Reviews (MathSciNet): MR1454579
Zentralblatt MATH: 0923.60026
Digital Object Identifier: doi:10.1016/S0304-4149(97)00018-5 - [5] Cattiaux, P. and Guillin, A. (2008). Deviation bounds for additive functionals of Markov processes. ESAIM Probab. Stat. 12 12–29 (electronic).Mathematical Reviews (MathSciNet): MR2367991
Zentralblatt MATH: 1183.60011
Digital Object Identifier: doi:10.1051/ps:2007032 - [6] Chen, M. F. and Wang, F. Y. (1994). Application of coupling method to the first eigenvalue on manifold. Sci. China Ser. A 37 1–14.Mathematical Reviews (MathSciNet): MR1308707
- [7] Djellout, H., Guillin, A. and Wu, L. (2004). Transportation cost-information inequalities and applications to random dynamical systems and diffusions. Ann. Probab. 32 2702–2732.Mathematical Reviews (MathSciNet): MR2078555
Zentralblatt MATH: 1061.60011
Digital Object Identifier: doi:10.1214/009117904000000531
Project Euclid: euclid.aop/1091813628 - [8] Dobrušin, R. L. (1970). Definition of a system of random variables by means of conditional distributions. Teor. Verojatnost. i Primenen. 15 469–497.Mathematical Reviews (MathSciNet): MR298716
- [9] Dobrushin, R. L. (1996). Perturbation methods of the theory of Gibbsian fields. In Lectures on Probability Theory and Statistics (Saint-Flour, 1994). Lecture Notes in Math. 1648 1–66. Springer, Berlin.Mathematical Reviews (MathSciNet): MR1600880
Zentralblatt MATH: 0871.60086
Digital Object Identifier: doi:10.1007/BFb0095674 - [10] Dobrushin, R. L. and Shlosman, S. B. (1985). Constructive criterion for the uniqueness of Gibbs field. In Statistical Physics and Dynamical Systems (Köszeg, 1984). Progress in Probability 10 347–370. Birkhäuser, Boston, MA.
- [11] Diaconis, P. and Saloff-Coste, L. (1996). Logarithmic Sobolev inequalities for finite Markov chains. Ann. Appl. Probab. 6 695–750.Mathematical Reviews (MathSciNet): MR1410112
Zentralblatt MATH: 0867.60043
Digital Object Identifier: doi:10.1214/aoap/1034968224
Project Euclid: euclid.aoap/1034968224 - [12] Guillin, A., Léonard, C., Wu, L. and Yao, N. (2009). Transportation-information inequalities for Markov processes. Probab. Theory Related Fields 144 669–695.Mathematical Reviews (MathSciNet): MR2496446
Zentralblatt MATH: 1169.60304
Digital Object Identifier: doi:10.1007/s00440-008-0159-5 - [13] Jacod, J. and Shiryaev, A. N. (2003). Limit Theorems for Stochastic Processes, 2nd ed. Grundlehren der Mathematischen Wissenschaften [Fundamental Principles of Mathematical Sciences] 288. Springer, Berlin.Mathematical Reviews (MathSciNet): MR1943877
- [14] Joulin, A. (2007). Poisson-type deviation inequalities for curved continuous-time Markov chains. Bernoulli 13 782–798.Mathematical Reviews (MathSciNet): MR2348750
Digital Object Identifier: doi:10.3150/07-BEJ6039
Project Euclid: euclid.bj/1186503486 - [15] Joulin, A. (2009). A new Poisson-type deviation inequality for Markov jump processes with positive Wasserstein curvature. Bernoulli 15 532–549.Mathematical Reviews (MathSciNet): MR2543873
Digital Object Identifier: doi:10.3150/08-BEJ158
Project Euclid: euclid.bj/1241444901 - [16] Lezaud, P. (1998). Chernoff-type bound for finite Markov chains. Ann. Appl. Probab. 8 849–867.Mathematical Reviews (MathSciNet): MR1627795
Zentralblatt MATH: 0938.60027
Digital Object Identifier: doi:10.1214/aoap/1028903453
Project Euclid: euclid.aoap/1028903453 - [17] Levin, D. A., Peres, Y. and Wilmer, E. L. (2009). Markov Chains and Mixing Times. Amer. Math. Soc., Providence, RI.
- [18] Martinelli, F. (2004). Relaxation times of Markov chains in statistical mechanics and combinatorial structures. In Probability on Discrete Structures. Encyclopaedia of Mathematical Sciences 110 175–262. Springer, Berlin.
- [19] Meyn, S. P. and Tweedie, R. L. (1993). Markov Chains and Stochastic Stability. Springer, London.Mathematical Reviews (MathSciNet): MR1287609
- [20] Oliveira, R. I. (2009). On the convergence to equilibrium of Kac’s random walk on matrices. Ann. Appl. Probab. 19 1200–1231.Mathematical Reviews (MathSciNet): MR2537204
Zentralblatt MATH: 1173.60343
Digital Object Identifier: doi:10.1214/08-AAP550
Project Euclid: euclid.aoap/1245071024 - [21] Ollivier, Y. (2007). Ricci curvature of metric spaces. C. R. Math. Acad. Sci. Paris 345 643–646.Mathematical Reviews (MathSciNet): MR2371483
Zentralblatt MATH: 1132.53011
Digital Object Identifier: doi:10.1016/j.crma.2007.10.041 - [22] Ollivier, Y. (2009). Ricci curvature of Markov chains on metric spaces. J. Funct. Anal. 256 810–864.Mathematical Reviews (MathSciNet): MR2484937
Zentralblatt MATH: 1181.53015
Digital Object Identifier: doi:10.1016/j.jfa.2008.11.001 - [23] Peres, Y. (2005). Mixing for Markov chains and spin systems. Available at http://www.stat.berkeley.edu/~peres/ubc.pdf.
- [24] Roberts, G. O. and Rosenthal, J. S. (2004). General state space Markov chains and MCMC algorithms. Probab. Surv. 1 20–71 (electronic).Mathematical Reviews (MathSciNet): MR2095565
Zentralblatt MATH: 1189.60131
Digital Object Identifier: doi:10.1214/154957804100000024
Project Euclid: euclid.ps/1099928648 - [25] Rudolf, D. Error bounds for computing the expectation by Markov chain Monte Carlo. Preprint. Available at arXiv:0906.2359.Mathematical Reviews (MathSciNet): MR2475305
Zentralblatt MATH: 1160.65004
Digital Object Identifier: doi:10.1016/j.jco.2008.05.005 - [26] Villani, C. (2003). Topics in Optimal Transportation. Graduate Studies in Mathematics 58. Amer. Math. Soc., Providence, RI.
- [27] Wu, L. (2000). A deviation inequality for non-reversible Markov processes. Ann. Inst. H. Poincaré Probab. Statist. 36 435–445.Mathematical Reviews (MathSciNet): MR1785390
Zentralblatt MATH: 0972.60003
Digital Object Identifier: doi:10.1016/S0246-0203(00)00135-7
- You have access to this content.
- You have partial access to this content.
- You do not have access to this content.
More like this
- Ricci curvature of Markov chains on Polish spaces revisited
Gong, Fu-Zhou, Liu, Yuan, and Wen, Zhi-Ying, Osaka Journal of Mathematics, 2013 - Convergence rate and concentration inequalities for Gibbs sampling in high dimension
Wang, Neng-Yi and Wu, Liming, Bernoulli, 2014 - Nonasymptotic analysis of adaptive and annealed Feynman–Kac particle models
Giraud, François and Del Moral, Pierre, Bernoulli, 2017
- Ricci curvature of Markov chains on Polish spaces revisited
Gong, Fu-Zhou, Liu, Yuan, and Wen, Zhi-Ying, Osaka Journal of Mathematics, 2013 - Convergence rate and concentration inequalities for Gibbs sampling in high dimension
Wang, Neng-Yi and Wu, Liming, Bernoulli, 2014 - Nonasymptotic analysis of adaptive and annealed Feynman–Kac particle models
Giraud, François and Del Moral, Pierre, Bernoulli, 2017 - Concentration bounds for stochastic approximations
Frikha, Noufel and Menozzi, Stéphane, Electronic Communications in Probability, 2012 - Transportation and concentration inequalities for bifurcating Markov chains
Bitseki Penda, S. Valère, Escobar-Bach, Mikael, and Guillin, Arnaud, Bernoulli, 2017 - A survey of Ricci curvature for metric spaces and Markov chains
Ollivier, Yann, , 2010 - Moderate deviations for empirical measures of Markov chains: lower
bounds
de Acosta, A., The Annals of Probability, 1997 - On Conditional Least Squares Estimation for Stochastic Processes
Klimko, Lawrence A. and Nelson, Paul I., The Annals of Statistics, 1978 - Convergence Control Methods for Markov Chain Monte Carlo Algorithms
Robert, Christian P., Statistical Science, 1995 - Approximations of the Wiener sausage and its curvature measures
Rataj, Jan, Spodarev, Evgeny, and Meschenmoser, Daniel, The Annals of Applied Probability, 2009