Best choices for regularization parameters in learning theory: On the bias-variance problem

被引：198
作者：
Cucker, F
Smale, S
机构：
[1] City Univ Hong Kong, Dept Math, Hong Kong, Hong Kong, Peoples R China
[2] Univ Calif Berkeley, Dept Math, Berkeley, CA 94720 USA
来源：
FOUNDATIONS OF COMPUTATIONAL MATHEMATICS | 2002年 / 2卷 / 04期
关键词：
D O I：
10.1007/s102080010030
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
[No abstract available]
引用
收藏
页码：413 / 428
页数：16
相关论文
共 15 条
[1]  
BARRON AR, 1994, MACH LEARN, V14, P115, DOI 10.1007/BF00993164
[2]  
BARRON AR, 1995, PROBAB THEORY REL, V113, P301
[3]  
Bishop C. M., 1995, NEURAL NETWORKS PATT
[4]  
Cucker F, 2002, B AM MATH SOC, V39, P1
[5]   Regularization networks and support vector machines [J].
Evgeniou, T ;
Pontil, M ;
Poggio, T .
ADVANCES IN COMPUTATIONAL MATHEMATICS, 2000, 13 (01) :1-50
[6]   GENERALIZED CROSS-VALIDATION AS A METHOD FOR CHOOSING A GOOD RIDGE PARAMETER [J].
GOLUB, GH ;
HEATH, M ;
WAHBA, G .
TECHNOMETRICS, 1979, 21 (02) :215-223
[7]  
Ivanov V.V, 1976, The Theory of Approximate Methods
[8]   ASYMPTOTICALLY MINIMAX ADAPTIVE ESTIMATION .1. UPPER-BOUNDS - OPTIMALLY ADAPTIVE ESTIMATES [J].
LEPSKII, OV .
THEORY OF PROBABILITY AND ITS APPLICATIONS, 1991, 36 (04) :682-697
[9]  
LEPSKII OV, 1992, THEOR PROBAB APPL+, V37, P433
[10]  
Mignotte Maurice, 1992, MATH COMPUTER ALGEBR
12