We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without a priori knowledge of the class at hand.
CITATION STYLE
Bartlett, P. L., Bousquet, O., & Mendelson, S. (2002). Localized rademacher complexities. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2375, pp. 44–58). Springer Verlag. https://doi.org/10.1007/3-540-45435-7_4
Mendeley helps you to discover research relevant for your work.