Fast learning rates for plug-in classifiers

Annals of Statistics

Volumn 35, Issue 2, 2007, Pages 608-633

  Audibert, Jean Yves ^a   Tsybakov, Alexandre B ^b  

^a UNIVERSITÉ PARIS EST   (France)

^b SORBONNE UNIVERSITÉ   (France)

Author keywords

Classification; Excess risk; Fast rates of convergence; Minimax lower bounds; Plug in classifiers; Statistical learning

Indexed keywords

EID: 34547706430     PISSN: 00905364     EISSN: None     Source Type: Journal    
DOI: 10.1214/009053606000001217     Document Type: Article

References (27)

1. AUDIBERT, J.-Y. (2004). Classification under polynomial entropy and margin assumptions and randomized estimators. Preprint, Laboratoire de Probabilités et Modèles Aléatoires, Univ. Paris VI and VII. Available at www.proba.jussieu.fr/mathdoc/textes/PMA-908.pdf.
2. AUDIBERT, J.-Y. and TSYBAKOV, A. B. (2005). Fast learning rates for plug-in classifiers under the margin condition. Preprint, Laboratoire de Probabilités et Modèles Aléatoires, Univ. Paris VI and VII. Available at arxiv.org/abs/math/0507180.
3. BARTLETT, P. L., JORDAN, M. I. and MCAULIFFE, J. D. (2006). Convexity, classification and risk bounds. J. Amer. Statist. Assoc. 101 138-156. MR2268032
4. α. Mat. Sb. (N.S.) 73 331-355. MR0217487
5. BLANCHARD, G., BOUSQUET, O. and MASSART, P. (2004). Statistical performance of support vector machines. Unpublished manuscript. Available at www.kyb.mpg.de/publications/pss/ps2731.ps.
6. BLANCHARD, G., LUGOSI, G. and VAYATIS, N. (2004). On the rate of convergence of regularized boosting classifiers. J. Mach. Learn. Res. 4 861-894. MR2076000
7. BOUCHERON, S., BOUSQUET, O. and LUGOSI, G. (2005). Theory of classification: A survey of some recent advances. ESAIM Probab. Stat. 9 323-375. MR2182250
8. DEVROYE, L., GYÖRFI, L. and LUGOSI, G. (1996). A Probabilistic Theory of Pattern Recognition. Springer, New York. MR1383093
9. GYÖRFI, L., KOHLER, M., KRZYŻAK, A. and WALK, H. (2002). A Distribution-Free Theory of Nonparametric Regression. Springer, New York. MR 1920390
10. KOLMOGOROV, A. N. and TIHOMIROV, V. M. (1961). ε-entropy and ε-capacity of sets in functional space. Amer. Math. Soc. Transl. (2) 17 277-364. MR0124720
11. KOLTCHINSKII, V. (2006). Local Rademacher complexities and oracle inequalities in risk minimization (with discussion). Ann. Statist. 34 2593-2706.
12. KOLTCHINSKII, V. and BEZNOSOVA, O. (2005). Exponential convergence rates in classification. In Learning Theory. Lecture Notes in Comput. Sci. 3559 295-307. Springer, Berlin. MR2203269
13. KOROSTELËV, A. P. and TSYBAKOV, A. B. (1993). Minimax Theory of Image Reconstruction. Springer, New York. MR1226450
14. MAMMEN, E. and TSYBAKOV, A. B. (1999). Smooth discrimination analysis. Ann. Statist. 27 1808-1829. MR1765618
15. MASSART, P. and NÉDÉLEC, E. (2006). Risk bounds for statistical learning. Ann. Statist. 34 2326-2366. MR2291502
16. NEMIROVSKII, A. S., POLYAK, B. T. and TSYBAKOV, A. B. (1985). Rate of convergence of nonparametric estimators of maximum-likelihood type. Probl. Inform. Trans. 21 258-272. MR0820705
17. STEINWART, I. and SCOVEL, J. C. (2007). Fast rates for support vector machines using Gaussian kernels. Ann. Statist. 35 575-607.
18. STONE, C. J. (1982). Optimal global rates of convergence for nonparametric regression. Ann. Statist. 10 1040-1053. MR0673642
19. 1 penalty. Preprint, Univ. Leiden. Available at stat.ethz.ch/~geer/svm4.pdf.
20. TSYBAKOV, A.B. (2004). Optimal aggregation of classifiers in statistical learning. Ann. Statist. 32 135-166. MR2051002
21. TSYBAKOV, A. B. (2004). Introduction à l'estimation non-paramétrique. Springer, Berlin. MR2013911
22. TSYBAKOV, A. B. and VAN DE GEER, S. (2005). Square root penalty: Adaptation to the margin in classification and in edge estimation. Ann. Statist. 33 1203-1224. MR2195633
23. VAN DE GEER, S. (2000). Applications of Empirical Process Theory. Cambridge Univ. Press. MR1739079
24. VAPNIK, V. N. (1998). Statistical Learning Theory. Wiley, New York. MR1641250
25. VAPNIK, V. N. and CHERVONENKIS, A. YA. (1974). Theory of Pattern Recognition. Statistical Problems of Learning. Nauka, Moscow. (In Russian.) MR0474638
26. YANG, Y. (1999). Minimax nonparametric classification. I. Rates of convergence. II. Model selection for adaptation. IEEE Trans. Inform. Theory 45 2271-2292. MR1725115, MR1725116
27. YANG, Y. and BARRON, A. (1999). Information-theoretic determination of minimax rates of convergence. Ann. Statist. 27 1564-1599. MR1742500