Conditions for the convergence of evolutionary algorithms

被引：44

作者：

He, J

Yu, XH ^{[1
]}

机构：

[1] Univ Cent Queensland, Fac Informat & Commun, Rockhampton, Qld 4702, Australia

[2] No Jiaotong Univ, Dept Comp Sci, Beijing 100044, Peoples R China

来源：

JOURNAL OF SYSTEMS ARCHITECTURE | 2001年 / 47卷 / 07期

关键词：

evolutionary algorithms; Markov chain; convergence; convergence rate;

D O I：

10.1016/S1383-7621(01)00018-2

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a theoretical analysis of the convergence conditions for evolutionary algorithms. The necessary and sufficient conditions, necessary conditions, and sufficient conditions for the convergence of evolutionary algorithms to the global optima are derived, which describe their limiting behaviors. Their relationships are explored. Upper and lower bounds of the convergence rates of the evolutionary algorithms are given. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：601 / 612

页数：12

共 12 条

[1] Toward a Theory of Evolution Strategies: On the Benefits of Sex- the (mu/mu, lambda) Theory [J].

Beyer, Hans-Georg .

EVOLUTIONARY COMPUTATION, 1995, 3 (01) :81-111

[2]

CERF R, 1996, ARTIFICIAL EVOLUTION

[3]

DAVIS TE, 1991, P 4 C GEN ALG M KAUF

[4]

Eiben A. E., 1991, Parallel Problem Solving from Nature. 1st Workshop, PPSN 1 Proceedings, P4

[5] Theory of evolutionary algorithms: a bird's eye view [J].

Eiben, AE ;

Rudolph, G .

THEORETICAL COMPUTER SCIENCE, 1999, 229 (1-2) :3-9

[6] On the convergence rates of genetic algorithms [J].

He, J ;

Kang, LS .

THEORETICAL COMPUTER SCIENCE, 1999, 229 (1-2) :23-39

[7] CONVERGENCE ANALYSIS OF CANONICAL GENETIC ALGORITHMS [J].

RUDOLPH, G .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (01) :96-101

[8]

Rudolph G., 1998, Fundamenta Informaticae, V35, P67

[9]

Rudolph G, 1997, CONTROL CYBERN, V26, P375

[10]

Rudolph G., 1997, CONVERGENCE PROPERTI

← 1 2 →