Bartlett P, Bousquet O, Mendelson S. (2002). Localized Radeacher complexity Proceedings of the Annual Conference on Computational Learning Theory.

Bartlett P, Williamson R, Lee W. (1998). The importance of convexity in learning with squared loss IEEE Trans Inform Theory. 44

Mendelson S. (2002). Improving the sample complexity using global data IEEE Trans Inform Theory. 48

Mendelson S. (2003). On the performance of kernel classes JMLR. 4

Scholkopf B, Smola A, Williamson RC. (2001). Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators IEEE Trans Inform Theory. 47

Shawe-taylor J, Williamson RC, Bartlett PL, Guo Y. (2002). Covering numbers for support vector machines IEEE Trans Inform Theory. 48

Smale S, Chucker F. (2002). On the mathematical foundations of learning Bull Am Math Soc. 39

Stone CJ. (1982). Optimal global rates of convergence for nonparametric regression Ann Stat. 10

Wahba G. (1990). Splines models for observational data.

Yurinsky V. (1995). Sums and gaussian vectors.

Zhang T. (2002). Covering number bounds of certain regularized linear function classes J Mach Learn Res. 2

Zhang T. (2003). Leave-one-out bounds for kernel methods Neural Comput. 15

Zhang T. (2003). Effective dimension and generalization of kernel learning Neural information processing systems. 15

van_de_Geer S. (2000). Empirical processes in M-estimation.