Low cost high performance uncertainty quantification
Authors:
Open Access
- 15 November 2009
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Abstract
Uncertainty quantification in risk analysis has become a key application. In this context, computing the diagonal of inverse covariance matrices is of paramount importance. Standard techniques, that employ matrix factorizations, incur a cubic cost which quickly becomes intractable with the current explosion of data sizes. In this work we reduce this complexity to quadratic with the synergy of two algorithms that gracefully complement each other and lead to a radically different approach. First, we turned to stochastic estimation of the diagonal. This allowed us to cast the problem as a linear system with a relatively small number of multiple right hand sides. Second, for this linear system we developed a novel, mixed precision, iterative refinement scheme, which uses iterative solvers instead of matrix factorizations. We demonstrate that the new framework not only achieves the much needed quadratic cost but in addition offers excellent opportunities for scaling at massively parallel environments. We based our implementation on BLAS 3 kernels that ensure very high processor performance. We achieved a peak performance of 730 TFlops on 72 BG/P racks, with a sustained performance 73% of theoretical peak. We stress that the techniques presented in this work are quite general and applicable to several other important applications. Copyright © 2009 ACMKeywords
This publication has 11 references indexed in Scilit:
- An estimator for the diagonal of a matrixApplied Numerical Mathematics, 2007
- Mixed Precision Iterative Refinement Techniques for the Solution of Dense Linear SystemsThe International Journal of High Performance Computing Applications, 2007
- Optimizing task layout on the Blue Gene/L supercomputerIBM Journal of Research and Development, 2005
- Maximum likelihood training of subspaces for inverse covariance modeling2003
- Iterative Methods for Sparse Linear Systems2003
- On the Inverse of the Covariance Matrix in Portfolio AnalysisThe Journal of Finance, 1998
- Calculation of the Inverse of the CovarianceMathematical Geology, 1998
- Numerical Linear Algebra for High-Performance Computers1998
- ScaLAPACK Users' Guide1997
- A stochastic estimator of the trace of the influence matrix for laplacian smoothing splinesCommunications in Statistics - Simulation and Computation, 1990