BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20101116T231500Z
DTEND:20101117T010000Z
LOCATION:Main Lobby
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: We investigate the problem of fitting geospatial models to large spatial and climate datasets. The process of fitting a model fundamentally involves efficient computation of likelihoods. An exact solution of the problem for n observations requires computing the determinant and inverse of the nxn covariance matrix, which can be expensive for large n. We examine two modes of parallelization to overcome these limitations: multi-threaded (within single node) and distributed (across multiple nodes). =0AOn a single node, we used the Multi-threaded Cholesky implementation within R/LAPACK/BLAS to achieve a significant performance gain over the single threaded implementation. =0AFor a cluster of compute nodes, we implemented a distributed Cholesky decomposition using Rmpi. The resulting Cholesky decomposition utilized all available cores on a single node, as well as multiple nodes on the cluster. Our preliminary result suggests that the time required for analyzing 32k spatially indexed observations would only take a few hours on a moderate cluster of computing nodes instead of a week on a single core.
SUMMARY:Distributed Likelihoods Computation for Large Spatial Data
PRIORITY:3
END:VEVENT
END:VCALENDAR