Xiangping Hu (Department of Mathematics, Uio), gives a seminar in our usual Auditorium 4 at 14:15, Tuesday Nov. 5'th: Title: New approach for multivariate Gaussian random fields Abstract: We discuss how to construct multivariate GRFs and multivariate GRFs with oscillating covariance functions with systems of Stochastic Partial Differential Equations (SPDEs). By solving a system of SPDEs, we can construct multivariate GRFs. On the theoretical side, the notorious requirement of non-negative definiteness for the covariance matrix of the GRF is satisfied since the constructed covariance matrices with this approach are automatically symmetric positive definite. Using the approximate stochastic weak solutions to the systems of SPDEs, multivariate GRFs are represented by multivariate Gaussian Markov random fields (GMRFs) with sparse precision matrices. Therefore, on the computational side, the sparse structures make it possible to use numerical algorithms for sparse matrices to do fast sampling from the random fields and statistical inference. Some examples will be given in order to illustrate how to use the newly proposed approach.
Xiangping Hu
Xiangping Hu: New approach for multivariate Gaussian random fields
Published Nov. 2, 2013 4:24 PM
- Last modified Nov. 2, 2013 4:24 PM