Generalized Lehmer Mean for Success History based Adaptive Differential Evolution

被引：4

作者：

Stanovov, Vladimir ^{[1
,2
]}

Akhmedova, Shakhnaz ^{[1
]}

Semenkin, Eugene ^{[2
]}

Semenkina, Mariia ^{[3
]}

机构：

[1] Reshetnev Siberian State Univ, Krasnoyarskii Rabochii Ave 31, Krasnoyarsk 660037, Russia

[2] Siberian Fed Univ, Inst Math & Comp Sci, 79 Svobodny Pr, Krasnoyarsk 660041, Russia

[3] Univ Appl Sci Upper Austria, Heurist & Evolutionary Algorithms Lab HEAL, Softwarepk 11, A-4232 Hagenberg, Austria

来源：

IJCCI: PROCEEDINGS OF THE 11TH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE | 2019年

关键词：

Differential Evolution; Optimization; Parameter Control; Metaheuristic;

D O I：

10.5220/0008163600930100

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Differential Evolution (DE) is a highly competitive numerical optimization algorithm, with a small number of control parameters. However, it is highly sensitive to the setting of these parameters, which inspired many researchers to develop adaptation strategies. One of them is the popular Success-History based Adaptation (SHA) mechanism, which significantly improves the DE performance. In this study, the focus is on the choice of the metaparameters of the SHA, namely the settings of the Lehmer mean coefficients for scaling factor and crossover rate memory cells update. The experiments are performed on the LSHADE algorithm and the Congress on Evolutionary Computation competition on numerical optimization functions set. The results demonstrate that for larger dimensions the SHA mechanism with modified Lehmer mean allows a significant improvement of the algorithm efficiency. The theoretical considerations of the generalized Lehmer mean could be also applied to other adaptive mechanisms.

引用

页码：93 / 100

页数：8

共 12 条

[1] Algorithmic design issues in adaptive differential evolution schemes: Review and taxonomy [J].

Al-Dabbagh, Rawaa Dawoud ;

Neri, Ferrante ;

Idris, Norisma ;

Baba, Mohd Sapiyan .

SWARM AND EVOLUTIONARY COMPUTATION, 2018, 43 :284-311

[2]

Brest J, 2017, IEEE C EVOL COMPUTAT, P1311, DOI 10.1109/CEC.2017.7969456

[3]

Bullen P., 2003, HDB MEANS THEIR INEQ

[4] Infeasibility and structural bias in differential evolution [J].

Caraffini, Fabio ;

Kononova, Anna V. ;

Corne, David .

INFORMATION SCIENCES, 2019, 496 :161-179

[5] Recent advances in differential evolution - An updated survey [J].

Das, Swagatam ;

Mullick, Sankha Subhra ;

Suganthan, P. N. .

SWARM AND EVOLUTIONARY COMPUTATION, 2016, 27 :1-30

[6] Multi-start JADE with knowledge transfer for numerical optimization [J].

Peng, Fei ;

Tang, Ke ;

Chen, Guoliang ;

Yao, Xin .

2009 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-5, 2009, :1889-1895

[7] LSHADE Algorithm with Rank-Based Selective Pressure Strategy for Solving CEC 2017 Benchmark Problems [J].

Stanovov, Vladimir ;

Akhmedova, Shakhnaz ;

Semenkin, Eugene .

2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2018, :757-764

[8] Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces [J].

Storn, R ;

Price, K .

JOURNAL OF GLOBAL OPTIMIZATION, 1997, 11 (04) :341-359

[9]

Tanabe R, 2014, 2014 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), P1658, DOI 10.1109/CEC.2014.6900380

[10]

Tanabe R, 2013, 2013 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), P71

← 1 2 →