Abstract
Many applications require efficient sampling from Gaussian distributions. The method of choice depends on the dimension of the problem as well as the structure of the covariance- (Σ) or precision matrix (Q). The most common black-box routine for computing a sample is based on Cholesky factorization. In high dimensions, computing the Cholesky factor of Σ or Q may be prohibitive due to accumulation of more non-zero entries in the factor than is possible to store in memory. We compare different methods for computing the samples iteratively adapting ideas from numerical linear algebra. These methods assume that matrix vector products, Qv, are fast to compute. We show that some of the methods are competitive and faster than Cholesky sampling and that a parallel version of one method on a Graphical Processing Unit (GPU) using CUDA can introduce a speed-up of up to 30x. Moreover, one method is used to sample from the posterior distribution of petroleum reservoir parameters in a North Sea field, given seismic reflection data on a large 3D grid.
Similar content being viewed by others
References
Akhiezer, N.I.: Elements of the Theory of Elliptic Functions. American Mathematical Society, Providence (1990)
Allen, E.J., Baglama, J., Boyd, S.K.: Numerical approximation of the product of the square root of a matrix with a vector. Linear Algebra Appl. 310, 167–181 (2000)
Aune, E., Simpson, D.P.: Parameter estimation in high dimensional Gaussian distributions. arXiv:1105.5256v1 [stat.CO] (2011)
Banerjee, S., Gelfand, A.E., Finley, A., Sang, H.: Gaussian predictive process models for large spatial data sets. J. R. Stat. Soc. B 70, 209–226 (2008)
Belabbas, M., Wolfe, P.: Spectral methods in machine learning and new strategies for very large datasets. Proc. Natl. Acad. Sci. 106(2), 369 (2009)
Bell, N., Garland, M.: Implementing sparse matrix-vector multiplication on throughput-oriented processors. In: SC’09: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, pp. 1–11. ACM, New York (2009)
Benzi, M., Bertaccini, D.: Approximate inverse preconditioning for shifted linear systems. BIT Numer. Math. 43(2), 231–244 (2003)
Besag, J., York, J., Mollie, A.: Bayesian image restoration, with two applications in spatial statistics. Ann. Inst. Stat. Math. 43, 1–59 (1991)
Björck, Å.: Numerical Methods for Least Squares Problems, vol. 51. Society for Industrial Mathematics, Philadelphia (1996)
Buland, A., Omre, H.: Bayesian linearized AVO inversion. Geophysics 68, 185–198 (2003)
Buland, A., Kolbjørnsen, O., Omre, H.: Rapid spatially coupled AVO inversion in the Fourier domain. Geophysics 68, 824–836 (2003)
Cressie, N., Johannesson, G.: Fixed rank kriging for large spatial datasets. J. R. Stat. Soc. B 70, 209–226 (2008)
Davies, P.I., Higham, N.J.: Computing f(A)b for matrix functions f. In: QCD and Numerical Analysis III, pp. 15–24. Springer, Berlin (2005)
Frommer, A., Simoncini, V.: Matrix functions. In: Model Order Reduction: Theory, Research Aspects and Applications, pp. 275–304. Springer, Berlin (2008)
Golub, G.H., van Loan, C.F.: Matrix Computations, 3rd edn. John Hopkins University Press, Baltimore (1996)
Gray, R.: Toeplitz and Circulant Matrices: A Review. E-book (2006)
Hale, N., Higham, N.J., Trefethen, L.N.: Computing A α, log(A) and related matrix functions by contour integrals. SIAM J. Numer. Anal. 46, 2505–2523 (2008)
Hestenes, M., Stiefel, E.: Methods of conjugate gradients for solving linear systems. J. Res. Natl. Bur. Stand. 49, 409–436 (1952)
Higham, N.J.: Functions of Matrices: Theory and Computation. Society for Industrial and Applied Mathematics, Philadelphia (2008)
Ilic, M., Turner, I.W., Anh, V.: A numerical solution using an adaptively preconditioned lanczos method for a class of linear systems related with the fractional Poisson equation. J. Appl. Math. Stoch. Anal. 2008, 104525 (2008)
Ilic, M., Turner, I.W., Simpson, D.P.: A restarted Lanczos approximation to functions of a symmetric matrix. IMA J. Numer. Anal. 30, 1044–1061 (2010)
Jegerlehner, B.: Krylov space solvers for shifted linear systems. arXiv:hep-lat/9612014v1 (1996)
Lee, A., Yau, C., Giles, M.B., Doucet, A., Holmes, C.C.: On the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods. J. Comput. Graph. Stat. 19, 769–789 (2010)
Lindgren, F., Lindstrøm, J., Rue, H.: An explicit link between Gaussian fields and Gaussian Markov random fields: the SPDE approach. J. R. Stat. Soc. B 73, 423–498 (2011)
MATLAB: Version 7.11.0 (R2010b). The MathWorks Inc., Natick (2010)
Meurant, G., Strakos, Z.: The Lanczos and conjugate gradient algorithms in finite precision arithmetic. Acta Numer. 15, 471–542 (2006)
Parker, A., Fox, C.: Sampling Gaussian distributions in Krylov spaces with conjugate gradients. SIAM J. Sci. Comput. (2011, submitted)
Paul, M., Held, L., Toschke, A.M.: Multivariate modelling of infectious disease surveillance data. Stat. Med. 27, 6250–6267 (2008)
Rabben, T.E., Ursin, B., Tjelmeland, H.: Non-linear Bayesian joint inversion of seismic reflection coefficients. Geophys. J. Int. 173, 265–280 (2008)
Rasmussen, C., Wiliams, C.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Riley, J.: Solving systems of linear equations with a positive definite, symmetric, but possibly ill-conditioned matrix. Math. Tables Other Aids Comput. 9(51), 96–101 (1955)
Roberts, G., Sahu, S.: Updating schemes, correlation structure, blocking and parameterization for the Gibbs sampler. J. R. Stat. Soc., Ser. B, Stat. Methodol. 59(2), 291–317 (1997)
Rue, H.: Fast sampling of Gaussian Markov random fields. J. R. Stat. Soc. B 63, 325–338 (2001)
Rue, H., Held, L.: Gaussian Markov Random Fields. Chapman & Hall, London (2005)
Rue, H., Tjelmeland, H.: Fitting Gaussian Markov random fields to Gaussian fields. Scand. J. Stat. 29, 31–49 (2002)
Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. SIAM, Philadelphia (2003)
Saad, Y., Yeung, M., Erhel, J., Guyomarc’h, F.: A deflated version of the conjugate gradient algorithm. SIAM J. Sci. Comput. 21, 1909–1926 (1999)
Schneider, M., Willsky, A.: A Krylov subspace method for covariance approximation and simulation of random processes and fields. Multidimens. Syst. Signal Process. 14, 295–318 (2003)
Shewchuk, J.: An introduction to the conjugate gradient method without the agonizing pain. http://www.cs.colorado.edu/~jessup/csci5646/READINGS/painless-conjugate-gradient.pdf (1994)
Simon, H.: Analysis of the symmetric Lanczos algorithm with reorthogonalization methods. Linear Algebra Appl. 61, 101–131 (1984)
Simpson, D.: Krylov subspace methods for approximating functions of symmetric positive definite matrices with applications to applied statistics and anomalous diffusion. PhD thesis, School of Mathematical Sciences, Queensland Univ of Tech (2008)
Simpson, D., Turner, I., Pettitt, A.: Fast sampling from a Gaussian Markov random field using Krylov subspace approaches. Technical report, School of Mathematical Sciences, Queensland Univ. of Tech. (2008)
Stein, E.M., Shakarchi, R.: Complex Analysis. Princeton University Press, Princeton (2003)
Stovas, A., Ursin, B.: Reflection and transmission responses of layered transversely isotropic viscoelastic media. Geophys. Prospect. 51, 447–477 (2003)
Trefethen, L., Bau, D.: Numerical Linear Algebra. SIAM, Philadelphia (1997)
Tyrtyshnikov, E.E.: Optimal and superoptimal circulant preconditioners. SIAM J. Matrix Anal. Appl. 13, 459–473 (1990)
van den Eshof, J., Sleijpen, G.: Accurate conjugate gradients methods for families of shifted systems. Appl. Numer. Math. 49, 17–37 (2003)
Zolotarev, E.I.: Applications of elliptic functions to questions of functions deviating least and most from zero. Zap. Imp. Nauk St. Petersb. 30 (1877)
Acknowledgements
We thank Statoil for permission to use the Norne dataset, François Alouges for helpful discussion of the deformation method and Daniel P. Simpson for insightful discussions on the use of Krylov methods for computing matrix functions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Aune, E., Eidsvik, J. & Pokern, Y. Iterative numerical methods for sampling from high dimensional Gaussian distributions. Stat Comput 23, 501–521 (2013). https://doi.org/10.1007/s11222-012-9326-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-012-9326-8