Minimax learning rates for bipartite ranking and plug-in rules

Proceedings of the 28th International Conference on Machine Learning, ICML 2011

Volumn , Issue , 2011, Pages 441-448

  Clémençon, Stéphan ^a   Robbiano, Sylvain ^a  

^a INSTITUT TELECOM   (France)

Author keywords

[No Author keywords available]

Indexed keywords

BINARY CLASSIFICATION; COST-SENSITIVE CLASSIFICATION; LEARNING RATES; LOW NOISE; LOWER BOUNDS; MINIMAX; NON-PARAMETRIC; PLUG-IN RULES; PLUG-INS; RANKING RULES; REGRESSION FUNCTION;

LEARNING SYSTEMS;

EID: 80053453381     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (22)

1. Agarwal, S., Graepel, T., Herbrich, R., Har-Peled, S., and Roth, D. Generalization bounds for the AUC. JMLR, 6:393-425, 2005.
2. Audibert, J.Y. Fast learning rates in statistical inference through aggregation. Ann. Statist, 37:1591-1646, 2009.
3. Audibert, J.Y. and Tsybakov, A.B. Fast learning rates for plug-in classifiers. Ann. Statist, 32:608-633, 2007.
4. Clémençon, S. and Vayatis, N. On partitioning rules for bipartite ranking. In Proceedings of AISTATS, number 5, pp. 97-104. JMLR: W&CP, 2009a.
5. Clémençon, S. and Vayatis, N. Overlaying classifiers: a practical approach to optimal scoring. To appear in Constructive Approximation, 2009b.
6. Clémençon, S. and Vayatis, N. Tree-based ranking methods. IEEE Transactions on Information Theory, 55(9):4316-4336, 2009c.
7. Clémençon, S., Lugosi, G., and Vayatis, N. Ranking and scoring using empirical risk minimization. In Proceedings of COLT, 2005.
8. Clémençon, S., Lugosi, G., and Vayatis, N. Ranking and empirical risk minimization of U-statistics. Ann. Statist, 36(2):844-874, 2008.
9. D.M.Green and Swets, J.A. Signal detection theory and psychophysics. Wiley, 1966.
10. Dudley, R.M. Uniform Central Limit Theorems. Cambridge University Press, 1999.
11. Freund, Y., Iyer, R. D., Schapire, R. E., and Singer, Y. An efficient boosting algorithm for combining preferences. JMLR, 4:933-969, 2003.
12. Hanley, J.A. and McNeil, J. The meaning and use of the AUC. Radiology, (143):29-36, 1982.
13. Koltchinskii, V. and Beznosova, O. Exponential convergence rates in classification. In Proceedings of COLT, 2005.
14. Lecué, G. Classification with minimax fast rates for classes of bayes rules with sparse representation. Electronic Journal of Statistics, 2:741-773, 2008.
15. Mammen, E. and Tsybakov, A.B. Asympotical minimax recovery of the sets with smooth boundaries. Ann. Statist., 23(2):502-524, 1995.
16. Massart, P. Some applications of concentration inequalities to statistics. Ann. Fac. Sci. Toulouse Math., 9:245-303, 2000.
17. Massart, P. and Nédélec, E. Risk bounds for statistical learning. Ann. Statist., 34(5), 2006.
18. Rudin, C. Ranking with a P-Norm Push. In Proceedings of COLT, 2006.
19. Srebro, N., Sridharan, K., and Tewari, A. Smoothness, low noise and fast rates. In Proceedings of NIPS. 2010.
20. Stone, C.J. Optimal global rates of convergence for nonparametric regression. Ann. Statist., 10:1040-1053, 1982.
21. Tsybakov, A. Optimal aggregation of classifiers in statistical learning. Ann. Statist, 32(1):135-166, 2004. (Pubitemid 41449306)
22. Yang, Y. Minimax nonparametric classification. I. rates of convergence. II. model selection for adaptation. IEEE Trans. Inf. Theory, 45:2271-2292, 1999.