Abstract
We show that the Gibbs Sampler in the Gaussian case is closely linked to linear fixed point iterations. In fact stochastic linear iterations converge toward a stationary distribution under the same conditions as the classical linear fixed point one. Furthermore the covariance matrices are shown to satisify a related fixed point iteration, and consequently the Gibbs Sampler in the gaussian case corresponds to the classical Gauss-Seidel iterations on the inverse of the covariance matrix, and the stochastic over-relaxed Gauss-Seidel has the same limiting distribution as the Gibbs Sampler. Then an efficient method to simulate a gaussian vector is proposed. Finally numerical investigations are performed to understand the effect of the different strategies such as the initial ordering, the blocking and the updating order for iterations. The results show that in a geostatistical context the rate of convergence can be improved significantly compared to the standard case.
Similar content being viewed by others
REFERENCES
Amit, Y., and Grenader, U., 1991, Comparing sweep strategies for stochastic relaxations: Journal of Multivariate Analysis, v. 37, p. 197–222.
Armstrong, M., Galli, A., Le Loc'h, G., Eschard, R., and Geffroy, F., 2001, Plurigaussian simulations: Springer-Verlag, Berlin, 200 p.
Barone, P., and Frigessi, A., 1990, Improving stochastic relaxation for gaussian random fields: Probability in the Engineering and Informational Sciences, v. 4, p. 369–389.
Breiz, H., 1992, Analyse fonctionnelle: Théorie et applications, Masson, Paris, 234 p.
Dufflo, M., 1997, Random iterative models: Springer-Verlag, Berlin, 385 p.
Freulon, X., 1994, Conditional simulation of a Gaussian vector with linear and/or noisy observations, in Armstrong, M., and Dowd, P. A., eds., Geostatistical simulations: Kluwer, Dordrecht, p. 217–233.
Froberg, C.-E., 1964, Introduction to numerical analysis: Addison-Wesley, Reading, MA, 340 p.
Gantmacher, F. R., 1966, The theory of matrices (2 vols.): Chelsea, New York, 370 p.
Gao, H., and Galli, A., 1999, Hasting-Metropolis algorithm and its convergence properties. Internal report, Centre de Géostatistique.
Gastinel, N., 1966, Analyse numérique linéaire: Hermann, Paris, 364 p.
Householder, A. S., 1964, The theory of matrices in numerical analysis: Blaisdell, New York.
Lantuéjoul, C., 1994, Non conditional simulation of stationary isotropic multigaussian random functions, in Armstrong, M., and Dowd, P. A., eds., Geostatistical simulations: Kluwer, Dordrecht, p. 147–177.
Lantuéjoul, C., 1997, Iterative algorithms for conditional simulations, in Baafi, E. Y., and Schofield, N. A., eds., Geostatistics Wollongong '96, Vol. 1: Dordrecht: Kluwer, p. 27–40.
Lantuéjoul, C., 2001, Geostatistical simulation: Models and algorithms, Spinger-Verlag, Berlin, 250 p.
Le Loc'h, G., and Galli, A., 1997, Truncated plurigaussian method: Theoretical and practical points of view, in Baafi, E. Y., and Schofield, N. A., eds., GeostatisticsWollongong '96, Vol. 1: Dordrecht, Kluwer, p. 211–222.
Matheron, G., 1973, The intrinsic random functions and their applications: Adv. Appl. Prob., Vol. 5, p. 439–468.
Omre, H., and Tjelmeland, H., 1997, Petroleum geostatistics, in Baafi, E. Y., and Schofield, N. A., eds., Geostatistics Wollongong '96, Vol. 1: Dordrecht, Kluwer, p. 41–52.
Roberts, G. O., and Sahu, S. K., 1997, Updating scheme, Correlation structure, blocking and parametrization for the Gibbs sampler: J. R. Statist. Soc. B, v. 59, No. 2, p. 291–317.
Shinozuka, M., and Jan, C. M., 1972, Digital simulation of random processes and its applications. Journal of Sound and Vib., v. 25-1, p. 111–128.
Varga, R. S., 1962, Matrix iterative analysis: Prentice-Hall, New York, 322 p.
Wilkinson, J. H., 1965, The algebraic eigenvalue problem: Oxford University Press, New York, 662 p.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Galli, A., Gao, H. Rate of Convergence of the Gibbs Sampler in the Gaussian Case. Mathematical Geology 33, 653–677 (2001). https://doi.org/10.1023/A:1011094131273
Issue Date:
DOI: https://doi.org/10.1023/A:1011094131273