Best Choices for Regularization Parameters in Learning Theory: On the Bias-Variance Problem

Foundations of Computational Mathematics

Volumn 2, Issue 4, 2002, Pages 413-428

  Cucker, Felipe ^a   Smale, Steve ^b  

^a CITY UNIVERSITY OF HONG KONG   (Hong Kong)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BEST CHOICE; LEARNING THEORY; REGULARIZATION PARAMETERS;

COMPUTATIONAL METHODS;

EID: 0036436325     PISSN: 16153375     EISSN: 16153383     Source Type: Journal    
DOI: 10.1007/s102080010030     Document Type: Article

References (15)

1. A. R. Barron, Approximation and estimation bounds for artificial neural networks, Machine Learning 14 (1994), 115-133.
2. A. R. Barron, L. Birgé, and P. Massart, Risk bounds for model selection via penalisation, Probab. Theory Related Fields 113 (1995), 301-403.
3. C. M. Bishop, Neural Networks for Pattern Recognition, Cambridge University Press, Cambridge, 1995.
4. F. Cucker and S. Smale, On the mathematical foundations of learning, Bull. Amer. Math. Soc. 39 (2002), 1-49.
5. T. Evgeniou, M. Pontil, and T. Poggio, Regularization networks and support vector machines, Adv. in Comput. Math. 13 (2000), 1-50.
6. G. Golub, M. Heat, and G. Wahba, Generalized cross-validation as a method for choosing a good ridge parameter, Technometrics 21 (1979), 215-223.
7. V. V. Ivanov, The Theory of Approximate Methods and Their Application to the Numerical Solution of Singular Integral Equations, Nordhoff International, 1976.
8. O. V. Lepskii, Asymptotically minimax adaptive estimation. I: Upper bounds, optimally adaptive estimates, Theory Probab. Appl. 36 (1991), 682-697.
9. O. V. Lepskii, Asymptotically minimax adaptive estimation. II: Schemes without optimal adaption, adaptive estimators, Theory Probab. Appl. 37 (1992), 433-448.
10. M. Mignotte, Mathematics for Computer Algebra, Springer-Verlag, New York, 1992.
11. P. Niyogi and F. Girosi, On the relationship between generalization error, hypothesis complexity and sample complexity for radial basis functions, Neural Comput. 8 (1996), 819-842.
12. P. Niyogi and F. Girosi, Generalization bounds for function approximation from scattered noisy data, Adv. in Comput. Math. 50 (1999), 51-80.
13. A. N. Tikhonov and V. Y. Arsenin, Solutions of III-Posed Problems, W. H. Winston, 1977.
14. S. van de Geer, Empirical Processes in M-Estimation, Cambridge University Press, Cambridge, 2000.
15. D.-X. Zhou, The covering numbers in learning theory, J. Complexity 2001 (to appear).