Nonlinear function approximation: Computing smooth solutions with an adaptive greedy algorithm

Journal of Approximation Theory

Volumn 143, Issue 2, 2006, Pages 159-175

  Hofinger, Andreas ^a  

^a JOHANN RADON INSTITUTE FOR COMPUTATIONAL AND APPLIED MATHEMATICS   (Austria)

Author keywords

Data noise; Greedy algorithm; Nonlinear function approximation; Regularization theory

Indexed keywords

EID: 33750610677     PISSN: 00219045     EISSN: 10960430     Source Type: Journal    
DOI: 10.1016/j.jat.2006.03.016     Document Type: Article

References (24)

1. Barron A.R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39 3 (1993) 930-945
2. Bodenhofer U., Burger M., Engl H.W., and Haslinger J. Regularized data-driven construction of fuzzy controllers. J. Inverse Ill-Posed Probl. 2 (2002) 319-344
3. Burger M., and Hofinger A. Regularized greedy algorithms for network training with data noise. Computing 74 (2005) 1-22
4. Burger M., and Neubauer A. Error bounds for approximation with neural networks. J. Approx. Theory 112 (2001) 235-250
5. W. Cheney, W. Light, A Course in Approximation Theory, Brooks/Cole Publishing Company, 2000.
6. Cucker F., and Smale S. On the mathematical foundations of learning. Bull. Amer. Math. Soc., New Ser. 39 1 (2002) 1-49
7. DeVore R.A., Howard R., and Micchelli C. Optimal nonlinear approximation. Manuscr. Math. 63 (1989) 469-478
8. DeVore R.A., and Temlyakov V.N. Some remarks on greedy algorithms. Adv. Comput. Math. 5 (1996) 173-187
9. Dingankar A.T., and Sandberg I.W. A note on error bounds for approximation in inner product spaces. Circuits Syst. Signal Process. 15 4 (1996) 519-522
10. Donahue M., Gurvits L., Darken C., and Sontag E. Rates of convex approximation in non-Hilbert spaces. Constructive Approximation 13 2 (1997) 187-220
11. Friedman J.H., and Stuetzle W. Projection pursuit regression. J. Amer. Statist. Assoc. 76 376 (1981) 817-823
12. Girosi F., Jones M., and Poggio T. Regularization theory and neural networks architectures. Neural Comput. 7 (1995) 219-269
13. Hofinger A. Iterative regularization and training of neural networks (2003), master's thesis, University of Linz
14. A. Hofinger, F. Pillichshammer, Learning a function from noisy samples at a finite sparse set of points, submitted.
15. Jones L.K. On a conjecture of Huber concerning the convergence of projection pursuit regression. Ann. Statist. 15 2 (1987) 880-882
16. Jones L.K. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Ann. Stat. 20 1 (1992) 608-613
17. Jones L.K. Local greedy approximation for nonlinear regression and neural network training. Ann. Statist. 28 5 (2000) 1379-1389
18. Lee W.S., Bartlett P.L., and Williamson R.C. Efficient agnostic learning of neural networks with bounded fan-in. IEEE Trans. Inform. Theory 42 6, part 2 (1996) 2118-2132
19. Niyogi P., and Girosi F. Generalization bounds for function approximation from scattered noisy data. Adv. Comput. Math. 10 (1999) 51-80
20. Pinkus A. n-Widths in Approximation Theory (1985), Springer, Berlin, Heidelberg
21. Rejto{combining double acute accent} L., and Walter G.G. Remarks on projection pursuit regression and density estimation. Stochastic Anal. Appl. 10 2 (1992) 213-222
22. Smale S., and Zhou D.-X. Shannon sampling and function reconstruction from point values. Bull. Amer. Math. Soc. New Ser. 41 3 (2004) 279-305
23. Temlyakov V.N. Weak greedy algorithms. Adver. Comput. Math. 12 2-3 (2000) 213-227
24. Temlyakov V.N. Nonlinear methods of approximation. Found. Comput. Math. 3 1 (2003) 33-107