Approximate Minimization of the Regularized Expected Error over Kernel Models

References

• Aarts E., Korst J.Simulated Annealing and Boltzmann Machines: A Stochastic Approach to Combinatorial Optimization and Neural Computing (1989) (John Wiley & Sons, New York) Google Scholar
• Aizerman M. A., Braverman E. M., Rozonoer L. I. Theoretical foundations of the potential function method in pattern recognition learning. Automation Remote Control (1964) 25:821–837Google Scholar
• Alessandri A., Sanguineti M., Maggiore M. Optimization-based learning with bounded error for feedforward neural networks. IEEE Trans. Neural Networks (2002) 13(2):261–273Crossref, Google Scholar
• Aronszajn N. Theory of reproducing kernels. Trans. Amer. Math. Soc. (1950) 68(3):337–404Crossref, Google Scholar
• Barron A. R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory (1993) 39(33):930–945Crossref, Google Scholar
• Berg C., Christensen J. P. R., Ressel P.Harmonic Analysis on Semigroups (1984) (Springer-Verlag, New York) Crossref, Google Scholar
• Berlinet A., Thomas-Agnan C.Reproducing Kernel Hilbert Spaces in Probability and Statistics (2004) (Springer)Crossref, Google Scholar
• Bertero M. Linear inverse and ill-posed problems. Adv. Electronics Electron Phys. (1989) 75:1–120Crossref, Google Scholar
• Bertsekas D. P.Nonlinear Programming (1999) (Athena Scientific, Belmont, MA) Google Scholar
• Bertsekas D. P., Tsitsiklis J. N.Neuro-Dynamic Programming (1996) (Athena Scientific, Belmont, MA) Google Scholar
• Borwein J., Lewis A.Convex Analysis and Nonlinear Optimization. CMS Books in Mathematics (2000) (Springer, New York) Crossref, Google Scholar
• Burger M., Neubauer A. Analysis of Tikhonov regularization for function approximation by neural networks. Neural Networks (2003) 16:79–90Crossref, Google Scholar
• Chen S. S., Donoho D. L., Saunders M. A. Atomic decomposition by Basis Pursuit. SIAM J. Sci. Comput. (1998) 20:33–61Crossref, Google Scholar
• Cortes C., Vapnik V. Support-vector networks. Machine Learn. (1995) 20:273–297Crossref, Google Scholar
• Cucker F., Smale S. On the mathematical foundations of learning. Bull. AMS (2002) 39:1–49Crossref, Google Scholar
• Dontchev A. L.Perturbations, Approximations and Sensitivity Analysis of Optimal Control Systems. Lecture Notes in Control and Information Sciences (1983) 52(Springer-Verlag, Berlin) Crossref, Google Scholar
• Dunford N., Schwartz J. T.Linear Operators. Part II: Spectral Theory (1963) (Interscience Publishers, New York) Google Scholar
• Fine T. L.Feedforward Neural Network Methodology (1999) (Springer)Google Scholar
• Friedman A.Modern Analysis (1982) (Dover, New York) Google Scholar
• Girosi F. An equivalence between sparse approximation and support vector machines. Neural Comput. (1998) 10:1455–1480Crossref, Google Scholar
• Girosi F., Jones M., Poggio T. Regularization theory and neural networks architectures. Neural Comput. (1995) 7:219–269Crossref, Google Scholar
• Goldberg D. E.Genetic Algorithms in Search, Optimization, and Machine Learning (1989) (Addison-Wesley)Google Scholar
• Grippo L. Convergent on-line algorithms for supervised learning in neural networks. IEEE Trans. Neural Networks (2000) 11(6):1284–1299Crossref, Google Scholar
• Jones L. K. A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Ann. Statist. (1992) 20(1):608–613Crossref, Google Scholar
• Kimeldorf G. S., Wahba G. A correspondence between Bayesian estimation on stochastic processes and smoothing by splines. Ann. Math. Statist. (1970) 41(2):495–502Crossref, Google Scholar
• Kimeldorf G. S., Wahba G. Some results on Tchebyceffian spline functions. J. Math. Anal. Appl. (1971) 33(1):82–95Crossref, Google Scholar
• Kůrková V., Sanguineti M. Comparison of worst-case errors in linear and neural network approximation. IEEE Trans. Inform. Theory (2002) 48(1):264–275Crossref, Google Scholar
• Kůrková V., Sanguineti M. Error estimates for approximate optimization by the extended Ritz method. SIAM J. Optim. (2005a) 15(2):261–287Crossref, Google Scholar
• Kůrková V., Sanguineti M. Learning with generalization capability by kernel methods of bounded complexity. J. Complexity (2005b) 21:350–367Crossref, Google Scholar
• Kůrková V., Kainen P. C., Kreinovich V. Estimates of the number of hidden units and variation with respect to half-spaces. Neural Networks (1997) 10(6):1061–1068Crossref, Google Scholar
• Parzen E. An approach to time series analysis. Ann. Math. Statist. (1961) 32:951–989Crossref, Google Scholar
• Parzen E. Reproducing kernel hilbert spaces outline. (2006) . http://www.stat.tamu.edu/∼jianhua/rkhs/Manny.pdfGoogle Scholar
• Pisier G. Remarques sur un resultat non publié de B. Maurey. Seminaire d'Analyse Fonctionelle I(12) (1980-81) (École Polytechnique, Centre de Mathématiques, Palaiseau, France) Google Scholar
• Poggio T., Girosi F. Networks for approximation and learning. Proc. IEEE (1990) 78(9):1481–1497Crossref, Google Scholar
• Poggio T., Smale S. The mathematics of learning: Dealing with data. Notices of the AMS (2003) 50(5):537–544Google Scholar
• Schölkopf B., Smola A. J.Learning with Kernels (2002) (The MIT Press, Cambridge, MA) Google Scholar
• Schönberg I. J. Metric spaces and completely monotone functions. Ann. Math. (1938) 39(4):811–841Crossref, Google Scholar
• Tikhonov A. N. Solutions of incorrectly formulated problems and the regularization method. Soviet Math. Dokl. (1963) 4:1035–1038Google Scholar
• Vapnik V. N.Statistical Learning Theory (1998) (John Wiley & Sons, New York) Google Scholar
• Wahba G. Splines models for observational data. (1990) 59(SIAM, Philadelphia) CBMS-NSF Regional Conference Series in Applied MathematicsCrossref, Google Scholar
• Yin G. Rates of convergence for a class of global stochastic optimization algorithms. SIAM J. Optim. (1963) 10:99–120Crossref, Google Scholar