Regularization schemes for minimum error entropy principle

被引：70

作者：

Hu, Ting ^{[1
]}

Fan, Jun ^{[2
]}

Wu, Qiang ^{[3
]}

Zhou, Ding-Xuan ^{[4
]}

机构：

[1] Wuhan Univ, Sch Math & Stat, Wuhan 430072, Peoples R China

[2] Univ Wisconsin, Dept Stat, Madison, WI 53706 USA

[3] Middle Tennessee State Univ, Dept Math Sci, Murfreesboro, TN 37132 USA

[4] City Univ Hong Kong, Dept Math, Kowloon, Hong Kong, Peoples R China

来源：

ANALYSIS AND APPLICATIONS | 2015年 / 13卷 / 04期

基金：

美国国家科学基金会;

关键词：

Minimum error entropy; learning theory; reproducing kernel Hilbert space; regularization scheme;

D O I：

10.1142/S0219530514500110

中图分类号：

O29 [应用数学];

学科分类号：

070104 ;

摘要：

We introduce a learning algorithm for regression generated by a minimum error entropy (MEE) principle and regularization schemes in reproducing kernel Hilbert spaces. This empirical MEE algorithm is highly related to a scaling parameter arising from Parzen windowing. The purpose of this paper is to carry out consistency analysis when the scaling parameter is large. Explicit learning rates are provided. Novel approaches are proposed to overcome the difficulties in bounding the output function uniformly and in the special MEE feature that the regression function may not be a minimizer of the error entropy.

引用

页码：437 / 455

页数：19

共 18 条

[1] THEORY OF REPRODUCING KERNELS [J].

ARONSZAJN, N .

TRANSACTIONS OF THE AMERICAN MATHEMATICAL SOCIETY, 1950, 68 (MAY) :337-404

[2]

Cristianini Nello, 2000, An introduction to support vector machines and other kernel-based learning methods

[3]

Erdogmus D., 2000, Second International Workshop on Independent Component Analysis and Blind Signal Separation. Proceedings, P75

[4] Convergence properties and data efficiency of the minimum error entropy criterion in adaline training [J].

Erdogmus, D ;

Principe, JC .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2003, 51 (07) :1966-1978

[5] Blind source separation using Renyi's α-marginal entropies [J].

Erdogmus, D ;

Hild, KE ;

Principe, JC .

NEUROCOMPUTING, 2002, 49 :25-38

[6] An error-entropy minimization algorithm for supervised training of nonlinear adaptive systems [J].

Erdogmus, D ;

Principe, JC .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2002, 50 (07) :1780-1786

[7]

Fan J., 2013, PREPRINT

[8] Information theoretic clustering [J].

Gokcay, E ;

Principe, JC .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (02) :158-171

[9]

Hu T, 2013, J MACH LEARN RES, V14, P377

[10] ONLINE REGRESSION WITH VARYING GAUSSIANS AND NON-IDENTICAL DISTRIBUTIONS [J].

Hu, Ting .

ANALYSIS AND APPLICATIONS, 2011, 9 (04) :395-408

← 1 2 →