Consistency and convergence rates of one-class SVMs and related algorithms

Journal of Machine Learning Research

Volumn 7, Issue , 2006, Pages 817-854

  Vert, Régis ^a,b   Vert, Jean Philippe ^c  

^a Laboratoire Interdisciplinaire des Sciences du Numérique   (France)

^b Masagroup   (France)

^c PSL RESEARCH UNIVERSITY   (France)

Author keywords

Convex loss functions; Gaussian kernel RKHS; Kernel density estimation; One class SVM; Regularization

Indexed keywords

ASYMPTOTIC STABILITY; BANDWIDTH; COMPUTATIONAL COMPLEXITY; CONVERGENCE OF NUMERICAL METHODS; OPTIMIZATION;

CONVEX LOSS FUNCTIONS; GAUSSIAN KERNEL RKHS; KERNEL DENSITY ESTIMATION; ONE-CLASS SVM; REGULARIZATION;

ALGORITHMS;

EID: 33646554819     PISSN: 15337928     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (27)

1. N. Aronszajn. Theory of reproducing kernels. Trans. Am. Math. Soc., 68:337 - 404, 1950.
2. P. I. Bartlett, M. I. Jordan, and J. D. McAuliffe. Convexity, classification and risk bounds. J. Amer. Statist. Assoc., 101(473):138-156, 2006.
3. P. L. Bartlett and A, Tewari. Sparseness vs estimating conditional probabilities: Some asymptotic results. In Lecture Notes in Computer Science, volume 3120, pages 564-578. Springer, 2004.
4. P. L. Bartlett, O. Bousquet, and S. Mendelson. Local Rademacher complexities. Ann. Stat., 33(4): 1497-1537, 2005.
5. B. E. Boser, I. M. Guyon, and V. N. Vapnik. A training algorithm for optimal margin classifiers. In Proceedings of the 5th annual ACM workshop on Computational Learning Theory, pages 144-152. ACM Press, 1992.
6. R. A. DeVore and G. G. Lorentz. Constructive Approximation. Springer Grundlehren der Mathematischen Wissenschaften. Springer Verlag, 1993.
7. L. Devroye and G. Lugosi. Combinatorial Methods in Density Estimation. Springer Series in Statistics. Springer, 2000.
8. L. Devroye, L. Györfi, and G. Lugosi. A Probabilistic Theory of Pattern Recognition, volume 31 of Applications of Mathematics. Springer, 1996.
9. G. B. Folland. Fourier analysis and its applications. The Wadsworth & Brooks/Cole Mathematics Series. Wadsworth & Brooks/Cole Advanced Books & Software, Pacific Grove, CA, 1992.
10. J. A. Hartigan. Estimation of a convex density contour in two dimensions. J. Amer. Statist. Assoc., 82(397):267-270, 1987.
11. V. Koltchinskii. Localized Rademacher complexities. Manuscript, September 2003.
12. G. Lugosi and N. Vayatis. On the Bayes-risk consistency of regularized boosting methods. Ann. Stat., 32:30-55, 2004.
13. E. Mammen and A. Tsybakov. Smooth discrimination analysis. Ann. Stat., 27 (6): 1808-1829, 1999.
14. P. Massart. Some applications of concentration inequalities to statistics. Ann. Fac. Sc. Toulouse, IX (2):245-303, 2000.
15. M. T. Matache and V. Matache. Hilbert spaces induced by Toeplitz covariance kernels. In Lecture Notes in Control and Information Sciences, volume 280, pages 319-334. Springer, Jan 2002.
16. B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson. Estimating the support of a high-dimensional distribution. Neural Comput., 13:1443-1471, 2001.
17. B. W. Silverman. On the estimation of a probability density function by the maximum penalized likelihood method. Ann. Stat., 10:795-810, 1982.
18. I. Steinwart. Support vector machines are universally consistent. J. Complexity, 18:768-791, 2002.
19. I. Steinwart. Sparseness of support vector machines. J. Mach. Learn. Res., 4:1071-1105, 2003.
20. I. Steinwart. Consistency of support vector machines and other regularized kernel classifiers. IEEE Trans. Inform. Theory, 51(1):128-142, 2005a.
21. I. Steinwart. How to compare loss functions and their risks. Technical report, Los Alamos National Laboratory, 2005b.
22. I. Steinwart and C. Scovel. Fast rates for support vector machines using Gaussian kernels. Technical Report LA-UR 04-8796, Los Alamos National Laboratory, 2004.
23. I. Steinwart, D. Hush, and C. Scovel. An explicit description of the reproducing kernel Hilbert spaces of Gaussian RBF kernels. Technical Report LA-UR 04-8274, Los Alamos National Laboratory, 2004.
24. I. Steinwart, D. Hush, and Scovel C. A classification framework for anomaly detection. J. Mach. Learn. Res., 6:211-232, 2005.
25. A.N. Tikhonov and V.Y. Arsenin. Solutions of ill-posed problems. W.H. Winston, 1977.
26. A. B. Tsybakov. On nonparametric estimation of density level sets. Ann. Stat., 25:948-969, June 1997.
27. T. Zhang. Statistical behavior and consistency of classification methods based on convex risk minimization. Ann. Stat., 32:56-134, 2004.