Bounds on margin distributions in learning problems

 Access to full text

 Full (PDF)

1. [1] M. Anthony, P. Bartlett, Neural Network Learning: Theoretical Foundations, Cambridge University Press, 1999. Zbl0968.68126MR1741038
2. [2] P. Bartlett, The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network, IEEE Trans. Inform. Theory44 (1998) 525-536. Zbl0901.68177MR1607706
3. [3] C. Cortes, V. Vapnik, Support vector networks, Machine Learning20 (1995) 273-297. Zbl0831.68098
4. [4] L. Devroye, L. Györfi, G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer-Verlag, New York, 1996. Zbl0853.68150MR1383093
5. [5] R.M. Dudley, Uniform Central Limit Theorems, Cambridge University Press, 1999. Zbl0951.60033MR1720712
6. [6] E. Giné, V. Koltchinskii, J. Wellner, Ratio limit theorems for empirical processes, Preprint, 2003. Zbl1055.60019MR2073436
7. [7] B. Kégl, T. Linder, G. Lugosi, Data-dependent margin-based generalization bounds for classification, in: Helmbold D., Williamson B. (Eds.), Proc. of 14th Annual Conference on Computational Learning Theory, COLT2001, Lecture Notes in Artificial Intelligence, Springer, New York, 2001, pp. 368-384. Zbl0992.68091MR2042047
8. [8] V. Koltchinskii, D. Panchenko, Rademacher processes and bounding the risk of function learning, in: Giné E., Mason D., Wellner J. (Eds.), High Dimensional Probability II, Birkhäuser, Boston, 2000, pp. 444-459. Zbl1106.68385MR1857339
9. [9] V. Koltchinskii, D. Panchenko, Empirical margin distributions and bounding the generalization error of combined classifiers, Ann. Statist.30 (2002) 1-50. Zbl1012.62004MR1892654
10. [10] V. Koltchinskii, D. Panchenko, F. Lozano, Some new bounds on the generalization error of combined classifiers, in: Leen T.K., Dietterich T.G., Tresp V. (Eds.), Proc. of NIPS'2000, Advances in Neural Information Processing Systems, 13, MIT Press, 2001, pp. 245-251, URL: , http://www.boosting.org/. 
11. [11] V. Koltchinskii, D. Panchenko, F. Lozano, Further explanation of the effectiveness of voting methods: the game between margins and weights, in: Helmbold D., Williamson B. (Eds.), Proc. of 14th Annual Conference on Computational Learning Theory, COLT2001, Lecture Notes in Artif. Intell., Springer, New York, 2001, pp. 241-255. Zbl0992.68511MR2042039
12. [12] V. Koltchinskii, D. Panchenko, F. Lozano, Bounding the generalization error of convex combinations of classifiers: balancing the dimensionality and the margins, Ann. Appl. Probab.13 (1) (2003) 213-252. Zbl1073.62535MR1951998
13. [13] M. Ledoux, M. Talagrand, Probability in Banach Spaces, Springer-Verlag, New York, 1991. Zbl0748.60004MR1102015
14. [14] P. Massart, About the constants in Talagrand's concentration inequalities for empirical processes, Ann. Probab.28 (2000) 863-885. Zbl1140.60310MR1782276
15. [15] P. Massart, Some applications of concentration inequalities to statistics, Ann. Fac. Sci. Tolouse (IX) (2000) 245-303. Zbl0986.62002MR1813803
16. [16] R. Schapire, Y. Freund, P. Bartlett, W.S. Lee, Boosting the margin: a new explanation of effectiveness of voting methods, Ann. Statist.26 (1998) 1651-1687. Zbl0929.62069MR1673273
17. [17] M. Talagrand, A new look at independence, Ann. Probab.24 (1996) 1-34. Zbl0858.60019MR1387624
18. [18] M. Talagrand, New concentration inequalities in product spaces, Invent. Math.126 (1996) 505-563. Zbl0893.60001MR1419006
19. [19] A. Tsybakov, Optimal aggregation of classifiers in statistical learning, Preprint, 2002. MR2051002
20. [20] A.W. van der Vaart, J.A. Wellner, Weak Convergence and Empirical Processes. With Applications to Statistics, Springer-Verlag, New York, 1996. Zbl0862.60002MR1385671
21. [21] V. Vapnik, Statistical Learning Theory, Wiley, New York, 1998. Zbl0935.62007MR1641250