A Dimension Adaptive Combination Technique Using Localised Adaptation Criteria
- 959 Downloads
We present a dimension adaptive sparse grid combination technique for the machine learning problem of regression. A function over a d-dimensional space, which assumedly describes the relationship between the features and the response variable, is reconstructed using a linear combination of partial functions; these may depend only on a subset of all features. The partial functions, which are piecewise multilinear, are adaptively chosen during the computational procedure. This approach (approximately) identifies the anova-decomposition of the underlying problem. We introduce two new localized criteria, one inspired by residual estimators based on a hierarchical subspace decomposition, for the dimension adaptive grid choice and investigate their performance on real data.
Unable to display preview. Download preview PDF.
- 1.Mark Ainsworth and J.Tinsley Oden. A posteriori error estimation in finite element analysis. Wiley, 2000.Google Scholar
- 3.Jochen Garcke. Regression with the optimised combination technique. In W. Cohen and A. Moore, editors, 23rd ICML ’06, pages 321–328, 2006.Google Scholar
- 4.Jochen Garcke. A dimension adaptive sparse grid combination technique for machine learning. In Wayne Read, Jay W. Larson, and A. J. Roberts, editors, Proc. of 13th CTAC-2006, volume 48 of ANZIAM J., pages C725–C740, 2007.Google Scholar
- 6.M. Griebel, M. Schneider, and C. Zenger. A combination technique for the solution of sparse grid problems. In P. de Groen and R. Beauwens, editors, Iterative Methods in Linear Algebra, pages 263–281. IMACS, Elsevier, 1992.Google Scholar
- 7.M. Hegland. Adaptive sparse grids. In K. Burrage and Roger B. Sidje, editors, Proc. of 10th CTAC-2001, volume 44 of ANZIAM J., pages C335–C353, 2003.Google Scholar
- 9.Ivor W. Tsang, James T. Kwok, and Kimo T. Lai. Core vector regression for very large regression problems. In Luc De Raedt and Stefan Wrobel, editors, 22nd ICML 2005, pages 912–919. ACM, 2005.Google Scholar