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

被引：195

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：

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

页码：413 / 428

页数：16

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
Evgeniou, T
Pontil, M
Poggio, T
[J]. ADVANCES IN COMPUTATIONAL MATHEMATICS, 2000, 13 (01) : 1 - 50
[6] GENERALIZED CROSS-VALIDATION AS A METHOD FOR CHOOSING A GOOD RIDGE PARAMETER
GOLUB, GH
HEATH, M
WAHBA, G
[J]. 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
LEPSKII, OV
[J]. 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