ISSN 2071-8594

Russian academy of sciences

Editor-in-Chief

Gennady Osipov

M.G. Belyaev. Approximation problem for factorized data

Abstract.

We consider samples with factorial design of experiments (full or incomplete). Universal approximation methods don’t take into account peculiarities of such samples. We develop structural approximation method which is based on special function class and regularization. Optimal solution in this class can be found efficiently.

Keywords:

nonlinear regression, factorial design of experiments, Kronecker product.

PP. 24-39.

Full version of the article in pdf.

REFERENCES

1. Grihon S., Alestra S., Burnaev E., Prikhodko P. Optimization of Composite Structure based on Surrogate Modeling of Buckling Analysis // Trudy konf. ITiC 2012. S. 41-47.
2. Kuleshov A.P. Kognitivnye tekhnologii v adaptivnykh modelyahk slozhnykh obyektov. Informatsionnye tekhnologii i vychislitelnye sistemy. 2008. № 1. S. 18-29.
3. Bayarria M.J., Bergera J.O., Kennedya M. C. et al. Predicting Vehicle Crashworthiness: Validation of Computer Models for Functional and Hierarchical Data // Journal of the American Statistical Association. 2009. V. 104(487). P. 929-943.
4. Otchet po proektu “Bystryy aerodinamichskiy paschet komponovki passzhirskogo samoleta”. MNIIPU. 2007.
5. Stone C.J., Hansen M.H., Kooperberg C., Truong Y. K. Polynomial splines, their tensor products in extended linear modeling. Annals of Statistic. 1997. V. 25. N. 4. P. 1371-1470.
6. Barthelmann V., Novak E., Ritter K. High dimensional polynomial interpolation on sparse grids. Advances in Computational Mathematics. 2000. V. 12. N. 4. P. 273-288.
7. Dierckx P. Computation of least-squares spline approximations to data over incomplete grids. Computers & Mathematics with Applications. 1984. V. 10(3). P. 283-289.
8. Pisinger G., Zimmermann A. Linear least squares problems with data over incomplete grid. BIT Numerical Mathematics. 2007. V. 47. P. 809-824.
9. Paulo R. Default Priors for Gaussian Processes. The Annals of Statistics. 2005. V. 33(2). P. 556-582.
10. Friedman J.H. Multivariate adaptive regression splines. Annals of Statistic. 1991. V. 19. N. 1. P. 1-141.
11.de Boor C. A Practical Guide to Splines, 2nd edition. Springer-Verlag. Berlin. 2001.
12. Sch lkopf B., Herbrich R., Smola A. A generalized representer theorem. Computational Learning Theory. 2001. V. 2111. P. 416-426.
13. Kolda T. G., Bader B. W. Tensor Decompositions and Applications. SIAM Review. 2009. V. 51(3). P. 455-500.
14. van Loan C.F. The ubiquitous Kronecker product. Journal of Computational and Applied Mathematics. 2000. V. 123(1-2). P. 85-100.
15. Belyaev M.G. Approksimatsiya dannykh, porozhdennykh dekartovym proizvedeniyem. Trudy MIFI. 2013. T.5. № 3. S. 11-23.
16. Belyaev M.G., Burnaev E.V., Lyubin A.D. Metodika formirovaniya funktsionalnogo slovarya v zadache approksimatsii mnogomernoy zavisimosti. Sbornik dokladov konferentsii ММРО-15 (2011). S. 146-149.
17. Rasmussen C.E., Williams C.K.I. Gaussian processes for machine learning. MIT Press. Cambridge. 2006.
18. Golub G.H., van Loan C.F. Matrix Computations, 3rd edition. The Johns Hopkins University Press, 1996.
19. Nocedal J., Wright S. Numerical Optimization, 2nd Edition. Springer. 2006.
20. Tibshirani R., Hastie T., Friedman J. The elements of statistical learning: data mining, prediction and inference, 2nd edition. Springer. New York. 2009.
21. Matlab Neural Network Toolbox. http://www.mathworks.com/products/neural-network/index.html
22. GPML toolbox.http://www.gaussianprocess.org/gpml/code/matlab/doc/index.html