Geodesic
The Вayes regularization in the problem of function of many variables approximation
Matematičeskoe modelirovanie, Tome 15 (2003) no. 9, pp. 55-63.

Voir la notice de l'article provenant de la source Math-Net.Ru

The problem of approximation of multi-dimensional data is a typical inverse problem of the reconstruction of the causes by effects. As the majority of inverse problems, this problem relates to the type of the problems that are poorly determined or ill-posed. A stable solution is reached by the minimization of a regularized learning error. The goal of the regularization is to provide the correctness of the problem by limitation of a variety of admissible solutions. The quality of learning is directly connected with an optimal choice of a regularization. In the present paper we propose a method of an optimal regularization in the approximation problem based on a systematic Bayes approach. 
@article{MM_2003_15_9_a4,
     author = {A. S. Nuzhny and S. A. Shumsky},
     title = {The {{\CYRV}ayes} regularization in the problem of function of many variables approximation},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {55--63},
     publisher = {mathdoc},
     volume = {15},
     number = {9},
     year = {2003},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2003_15_9_a4/}
}
TY  - JOUR
AU  - A. S. Nuzhny
AU  - S. A. Shumsky
TI  - The Вayes regularization in the problem of function of many variables approximation
JO  - Matematičeskoe modelirovanie
PY  - 2003
SP  - 55
EP  - 63
VL  - 15
IS  - 9
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2003_15_9_a4/
LA  - ru
ID  - MM_2003_15_9_a4
ER  - 
%0 Journal Article
%A A. S. Nuzhny
%A S. A. Shumsky
%T The Вayes regularization in the problem of function of many variables approximation
%J Matematičeskoe modelirovanie
%D 2003
%P 55-63
%V 15
%N 9
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2003_15_9_a4/
%G ru
%F MM_2003_15_9_a4
A. S. Nuzhny; S. A. Shumsky. The Вayes regularization in the problem of function of many variables approximation. Matematičeskoe modelirovanie, Tome 15 (2003) no. 9, pp. 55-63. http://geodesic.mathdoc.fr/item/MM_2003_15_9_a4/

[1] David J. C. MacKay, Bayesian Interpolation, Computation and Systems California Institute of Technology 139-74 Pasadena CA91125

[2] F. Girosi, “An equivalence bftween Sparse Approximation and Support Vector Machines”, Neural Computation, 10 (1998), 1455–1480 | DOI

[3] T. Poggio, F. Girosi, “A Sparse Representation for Function Approximation”, Neural Computation, 10:6 (1998), 1445–1454 | DOI | MR

[4] H. Zhu, R. Rohwer, “No free lunch for cross-validation”, Neural Computation, 8 (1996), 1421–1426 | DOI

[5] Radford, Geoffrey E. Hinton, “A view of the EM algorithm that justifies incremental, sparse and other variants”, Learning in Graphical Models, ed. Michael I. Jordan, 1998

[6] M. Werman, D. Keren, “A Bayesian Method for Fitting Parametric and Nonparametric Models to Noisy Data”, IEEE Transactions on PAMI, 23:5 (2001), 528–534

[7] M. L. Vorontsov, A. V. Koryabin, V. I. Shmalgauzen, Upravlyaemye opticheskie sistemy, Nauka, M., 1988

[8] Vapnik V. N., The nature of statistical learning theory, Springer-Verlag, New York, 1995 | MR