@InProceedings{ Garcke.Griebel:2001*1, author = {J. Garcke and M. Griebel}, title = {On the parallelization of the sparse grid approach for data mining}, booktitle = {Large-Scale Scientific Computations, Third International Conference, LSSC 2001, Sozopol, Bulgaria}, note = {also as SFB 256 Preprint 721, Universit\"at Bonn, 2001}, series = {Lecture Notes in Computer Science}, volume = 2179, pages = {22-32}, publisher = {Springer}, editor = {S. Margenov and J. Wasniewski and P. Yalamov}, ps = {http://wissrech.ins.uni-bonn.de/research/pub/garcke/psm.ps.gz} , pdf = {http://wissrech.ins.uni-bonn.de/research/pub/garcke/psm.pdf} , abstract = {Recently we presented a new approach to the classification problem arising in data mining. It is based on the regularization network approach, but in contrast to other methods which employ ansatz functions associated to data points, we use basis functions coming from a grid in the usually high-dimensional feature space for the minimization process. To cope with the curse of dimensionality, we employ sparse grids. To be precise we use the sparse grid combination technique where the classification problem is discretized and solved on a sequence of conventional grids with uniform mesh sizes in each dimension. The sparse grid solution is then obtained by linear combination. The method scales linearly with the number of data points and is well suited for data mining applications where the amount of data is very large, but where the dimension of the feature space is moderately high. The computation on each grid of the sequence of grids is independent of each other and therefore can be done in parallel already on a coarse grain level. A second level of parallelization on a fine grain level can be introduced on each grid through the use of threading on shared-memory multi-processor computers. We describe the sparse grid combination technique for the classification problem, the two ways of parallelisation, and report on the results on a 10 dimensional data set. }, year = {2001}, annote = {series,data,parallel} }