DC models for spherical separation

被引：34

作者：

Astorino, A. ^{[1
]}

Fuduli, A. ^{[2
]}

Gaudioso, M. ^{[1
]}

机构：

[1] Univ Calabria, Dipartimento Elettron Informat & Sistemist, Ist Calcolo & Reti Ad Alte Prestazioni CNR, I-87036 Arcavacata Di Rende, CS, Italy

[2] Univ Calabria, Dipartimento Matemat, I-87036 Arcavacata Di Rende, CS, Italy

来源：

JOURNAL OF GLOBAL OPTIMIZATION | 2010年 / 48卷 / 04期

关键词：

Spherical separation; DC functions; DCA;

D O I：

10.1007/s10898-010-9558-0

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

We propose two different approaches for spherical separation of two sets. Both methods are based on minimizing appropriate nonconvex nondifferentiable error functions, which can be both expressed in a DC (Difference of two Convex) form. We tackle the problem by adopting the DC-Algorithm. Some numerical results on classical binary datasets are reported.

引用

页码：657 / 669

页数：13

共 19 条

[1] The DC (difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems [J].