Rademacher complexity in Neyman-Pearson classification |
| |
Authors: | Min Han Di Rong Chen Zhao Xu Sun |
| |
Institution: | (1) Department of Applied Mathematics, Beijing University of Technology, Beijing, 100124, P. R. China;(2) Department of Mathematics, and LMIB, Beijing University of Aeronautics and Astronautics, Beijing, 100083, P. R. China;(3) School of Applied Mathematics, Central University of Finance and Economics, Beijing, 100081, P. R. China |
| |
Abstract: | Neyman-Pearson(NP) criterion is one of the most important ways in hypothesis testing. It is also a criterion for classification.
This paper addresses the problem of bounding the estimation error of NP classification, in terms of Rademacher averages. We
investigate the behavior of the global and local Rademacher averages, and present new NP classification error bounds which
are based on the localized averages, and indicate how the estimation error can be estimated without a priori knowledge of
the class at hand.
Research supported in part by NSF of China under Grant Nos. 10801004, 10871015; supported in part by Startup Grant for Doctoral
Research of Beijing University of Technology |
| |
Keywords: | Neyman-Pearson lemma VC classes Rademacher complexity Neyman-Pearson classification |
本文献已被 维普 SpringerLink 等数据库收录! |
|