S. Arlot, Resampling and Model Selection, 2007.
URL : https://hal.archives-ouvertes.fr/tel-00198803

S. Arlot, V -fold cross-validation improved: V -fold penalization, 2008.
URL : https://hal.archives-ouvertes.fr/hal-00239182

S. Arlot, Model selection by resampling penalization, Electronic Journal of Statistics, vol.3, issue.0, pp.557-624, 2009.
DOI : 10.1214/08-EJS196
URL : https://hal.archives-ouvertes.fr/hal-00125455

S. Arlot and P. Massart, Data-driven calibration of penalties for least-squares regression, J. Mach. Learn. Res, vol.10, pp.245-279, 2009.
URL : https://hal.archives-ouvertes.fr/inria-00287631

J. Audibert, Classification under polynomial entropy and margin assumptions and randomized estimators, 2004.

J. Audibert and A. B. Tsybakov, Fast learning rates for plug-in classifiers, The Annals of Statistics, vol.35, issue.2, pp.608-633, 2007.
DOI : 10.1214/009053606000001217
URL : https://hal.archives-ouvertes.fr/hal-00160849

A. Barron, L. Birgé, and P. Massart, Risk bounds for model selection via penalization. Probab. Theory Related Fields, pp.301-413, 1999.
DOI : 10.1007/s004400050210

L. Peter, M. I. Bartlett, J. D. Jordan, and . Mcauliffe, Convexity, classification , and risk bounds, Journal of the American Statistical Association, vol.101, issue.473, pp.138-156, 2006.

L. Peter, S. Bartlett, P. Mendelson, and . Philips, Local complexities for empirical risk minimization, Learning theory, pp.270-284, 2004.

L. Birgé and P. Massart, Minimum Contrast Estimators on Sieves: Exponential Bounds and Rates of Convergence, Bernoulli, vol.4, issue.3, pp.329-375, 1998.
DOI : 10.2307/3318720

G. Blanchard, G. Lugosi, and N. Vayatis, On the rate of convergence of regularized boosting classifiers, J. Mach. Learn. Res, vol.4, issue.5, pp.861-894, 2004.

G. Blanchard, P. Massartann, and . Statist, Discussion: Local Rademacher complexities and oracle inequalities in risk minimization, The Annals of Statistics, vol.34, issue.6, pp.2593-26562664, 2006.
DOI : 10.1214/009053606000001037

L. Devroye and G. Lugosi, Lower bounds in pattern recognition and learning, Pattern Recognition, vol.28, issue.7, pp.1011-1018, 1995.
DOI : 10.1016/0031-3203(94)00141-8

B. Efron, Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation, Journal of the American Statistical Association, vol.78, issue.382, pp.316-331, 1983.
DOI : 10.1080/01621459.1983.10477973

V. Koltchinskii, Local Rademacher complexities and oracle inequalities in risk minimization, The Annals of Statistics, vol.34, issue.6, pp.2593-2656, 2006.
DOI : 10.1214/009053606000001019

G. Lecué, Simultaneous adaptation to the margin and to complexity in classification, The Annals of Statistics, vol.35, issue.4, pp.1698-1721, 2007.
DOI : 10.1214/009053607000000055

G. Lecué, Suboptimality of Penalized Empirical Risk Minimization in Classification, Lecture Notes in Artificial Intelligence, vol.4539, 2007.
DOI : 10.1007/978-3-540-72927-3_12

G. Lugosi, Pattern Classification and Learning Theory, Principles of nonparametric learning, pp.1-56, 2001.
DOI : 10.1007/978-3-7091-2568-7_1
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.127.3142

G. Lugosi and M. Wegkamp, Complexity regularization via localized random penalties, Ann. Statist, vol.32, issue.4, pp.1679-1697, 2004.

E. Mammen and A. B. Tsybakov, Smooth discrimination analysis, Ann. Statist, vol.27, issue.6, pp.1808-1829, 1999.

P. Massart, Concentration inequalities and model selection, volume 1896 of Lecture Notes in Mathematics, Lectures from the 33rd Summer School on Probability Theory held in Saint-Flour, 2003.

P. Massart and . Nédélec, Risk bounds for statistical learning, The Annals of Statistics, vol.34, issue.5, pp.2326-2366, 2006.
DOI : 10.1214/009053606000000786

A. B. Tsybakov, Optimal aggregation of classifiers in statistical learning, The Annals of Statistics, vol.32, issue.1, pp.135-166, 2004.
DOI : 10.1214/aos/1079120131
URL : https://hal.archives-ouvertes.fr/hal-00102142

B. Alexandre, S. A. Tsybakov, and . Van-de-geer, Square root penalty: adaptation to the margin in classification and in edge estimation, Ann. Statist, vol.33, issue.3, pp.1203-1224, 2005.

N. Vladimir and . Vapnik, Statistical learning theory, 1998.

N. Vladimir, A. Y. Vapnik, and . Chervonenkis, On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, pp.264-280, 1971.