Asymptotic normality of support vector machine variants and other regularized kernel methods

Journal of Multivariate Analysis

Volumn 106, Issue , 2012, Pages 92-117

  Hable, Robert ^a  

^a UNIVERSITY OF BAYREUTH   (Germany)

Author keywords

Asymptotic normality; Functional delta method; Hadamard differentiability; Nonparametric regression; Regularized kernel method; Support vector machine

Indexed keywords

EID: 84855784491     PISSN: 0047259X     EISSN: 10957243     Source Type: Journal    
DOI: 10.1016/j.jmva.2011.11.004     Document Type: Article

References (37)

1. Akerkar R. Nonlinear Functional Analysis 1999, Narosa Publishing House, New Delhi.
2. Bauer H. Measure and Integration Theory 2001, Walter de Gruyter & Co, Berlin.
3. Berlinet A., Thomas-Agnan C. Reproducing Kernel Hilbert Spaces in Probability and Statistics 2004, Kluwer Academic Publishers, Boston, MA.
4. Blanchard G., Bousquet O., Massart P. Statistical performance of support vector machines. Annals of Statistics 2008, 36(2):489-531.
5. Bourbaki N. Integration. I Chapters 1-6 2004, Springer-Verlag, Berlin, Translated from the 1959, 1965 and 1967 French originals by Sterling K. Berberian.
6. Caponnetto A., DeVito E. Optimal rates for the regularized least-squares algorithm. Foundations of Computational Mathematics 2007, 7(3):331-368.
7. Christmann A., Steinwart I. Consistency and robustness of kernel-based regression in convex risk minimization. Bernoulli 2007, 13(3):799-819.
8. Christmann A., Steinwart I. On robustness properties of convex risk minimization methods for pattern recognition. Journal of Machine Learning Research (JMLR) 2004, 5:1007-1034.
9. Christmann A., VanMessem A. Bouligand derivatives and robustness of support vector machines for regression. Journal of Machine Learning Research (JMLR) 2008, 9:915-936.
10. Dekel O., Shalev-Shwartz S., Singer Y. Smooth ε-insensitive regression by loss symmetrization. Journal of Machine Learning Research (JMLR) 2005, 6:711-741.
11. Denkowski Z., Migórski S., Papageorgiou N. An Introduction to Nonlinear Analysis: Theory 2003, Kluwer Academic Publishers, Boston.
12. Devroye L. Any discrimination rule can have an arbitrarily bad probability of error for finite sample size. IEEE Transactions on Pattern Analysis and Machine Intelligence 1982, 4:154-157.
13. Dudley R. Real Analysis and Probability 2002, Cambridge University Press, Cambridge, Revised reprint of the 1989 original.
14. Dunford N., Schwartz J. Linear Operators. I. General Theory 1958, Wiley-Interscience Publishers, New York.
15. Fernique X. Intégrabilité des vecteurs gaussiens. Competes Rendus Mathématique. Académic des Sciences. Paris, Séries A-B 1970, 270:A1698-A1699.
16. Griffel D. Applied Functional Analysis 2002, Dover Publications Inc, Mineola, NY, Revised reprint of the 1985 edition.
17. Hable R., Christmann A. On qualitative robustness of support vector machines. Journal of Multivariate Analysis 2011, 102:993-1007.
18. Hadamard J. Sur les problèmes aux dérivées partielles et leur signification physique. Princeton University Bulletin 1902, 13:49-52.
19. Hoffmann-Jørgensen J. Probability with a View Toward Statistics, vol. I 1994, Chapman & Hall, New York.
20. Jiang B., Zhang X., Cai T. Estimating the confidence interval for prediction errors of support vector machine classifiers. Journal of Machine Learning Research (JMLR) 2008, 9:521-540.
21. Koo J.-Y., Lee Y., Kim Y., Park C. A Bahadur representation of the linear support vector machine. Journal of Machine Learning Research (JMLR) 2008, 9:1343-1368.
22. Luenberger D. Optimization by Vector Space Methods 1969, John Wiley & Sons Inc, New York.
23. Megginson R.E. An Introduction to Banach Space Theory 1998, Springer-Verlag, New York.
24. Mendelson S., Neeman J. Regularization in kernel learning. Annals of Statistics 2010, 38(1):526-565.
25. Rousseeuw P.J. Maxbias curves. Encyclopedia of Statistical Sciences. Update vol. 3 1999, 441-443. Wiley, New York. S. Kotz, C.B. Read, D.L. Banks (Eds.).
26. Satô H. A remark on Landau-Shepp's theorem. Sankhyā 1971, 33:227-228.
27. Schechter M. An Introduction to Nonlinear Analysis 2004, Cambridge University Press, Cambridge.
28. Schölkopf B., Smola A.J. Learning with Kernels 2002, MIT Press, Cambridge.
29. Steinwart I., Christmann A. Support Vector Machines 2008, Springer, New York.
30. I. Steinwart, D. Hush, C. Scovel, Optimal rates for regularized least squares regression, Proceedings of the 22nd Conference on Learning Theory (COLT 2009).
31. Steinwart I., Scovel C. Fast rates for support vector machines using Gaussian kernels. Annals of Statistics 2007, 35(2):575-607.
32. Tsybakov A.B. Optimal aggregation of classifiers in statistical learning. Annals of Statistics 2004, 32(1):135-166.
33. van de Geer S.A. Applications of Empirical Process Theory 2000, Cambridge University Press, Cambridge.
34. van der Vaart A. Asymptotic Statistics 1998, Cambridge University Press, Cambridge.
35. van der Vaart A., Wellner J. Weak Convergence and Empirical Processes. With Applications to Statistics 1996, Springer, New York.
36. Vapnik V.N. Statistical Learning Theory 1998, John Wiley & Sons, New York.
37. Zhou D.-X. Capacity of reproducing kernel spaces in learning theory. IEEE Transactions on Information Theory 2003, 49(7):1743-1752.