To what extent evolutionary algorithms can benefit from a longer search?

被引:0
|
作者
Piotrowski, Adam P. [1 ]
Napiorkowski, Jaroslaw J. [1 ]
Piotrowska, Agnieszka E. [2 ]
机构
[1] Polish Acad Sci, Inst Geophys, Ks Janusza 64, PL-01451 Warsaw, Poland
[2] Univ Warsaw, Fac Polish Studies, Krakowskie Przedmiescie 26-28, PL-00927 Warsaw, Poland
关键词
Metaheuristics; Performance; Time; Differential evolution; Particle swarm optimization; Swarm intelligence; DIFFERENTIAL EVOLUTION; OPTIMIZATION; ENSEMBLE; STRATEGY;
D O I
10.1016/j.ins.2023.119766
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In many comparison papers Evolutionary Algorithms are stopped after a pre-defined number of function calls, which is a code-independent measure of computational time. This number of function calls is either defined by the inventors of particular benchmark problems, or set subjectively by the user for the specific problem. The question how much improvement could be achieved by Evolutionary Algorithms if they were given much more time is surprisingly rarely asked. In the present study we analyze improvements obtained by thirty Evolutionary Algorithms on four different benchmark sets, including one composed of 22 real-world problems, when the allowed number of function calls is extended ten times with respect to the values defined in the comparison criteria for the specific benchmark sets. We analyze how the prolonged search would affect the ranking of algorithms, how much improvement could be obtained by Evolutionary Algorithms in general, on what kind of problems the improvement will be achieved, and which type of algorithms would benefit most from such an extended search. We show that the improvements obtained in prolonged search are higher for real-world problems than for mathematical functions, and such improvements are mainly achieved by similar kinds of adaptive algorithms proposed relatively recently. Many metaheuristics fail to benefit from the extended search on most benchmark problems, or benefit only marginally.
引用
收藏
页数:22
相关论文
共 50 条
  • [1] Evolutionary algorithms:: From recombination to search distributions
    Mühlenbein, H
    Mahnig, T
    [J]. THEORETICAL ASPECTS OF EVOLUTIONARY COMPUTING, 2001, : 135 - 173
  • [2] Evolutionary Algorithms for Supertree Search
    Ficici, Sevan G.
    Liu, Enoch
    Fogel, Gary B.
    [J]. 2012 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2012,
  • [3] The Benefit of Recombination in Noisy Evolutionary Search
    Friedrich, Tobias
    Koetzing, Timo
    Krejca, Martin S.
    Sutton, Andrew M.
    [J]. ALGORITHMS AND COMPUTATION, ISAAC 2015, 2015, 9472 : 140 - 150
  • [4] The Benefit of Recombination in Noisy Evolutionary Search
    Friedrich, Tobias
    Koetzing, Timo
    Krejca, Martin S.
    Sutton, Andrew M.
    [J]. PROCEEDINGS OF THE 2016 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'16 COMPANION), 2016, : 161 - 162
  • [5] From evolutionary operation to parallel direct search: Pattern search algorithms for numerical optimization
    Torczon, V
    Trosset, MW
    [J]. MINING AND MODELING MASSIVE DATA SETS IN SCIENCE, ENGINEERING, AND BUSINESS WITH A SUBTHEME IN ENVIRONMENTAL STATISTICS, 1997, 29 (01): : 396 - 401
  • [6] Up to What Extent Does Dravet Syndrome Benefit From Neurostimulation Techniques?
    Ding, Jiangwei
    Wang, Lei
    Li, Wenchao
    Wang, Yangyang
    Jiang, Shucai
    Xiao, Lifei
    Zhu, Changliang
    Hao, Xiaoyan
    Zhao, Jiali
    Kong, Xuerui
    Wang, Ziqin
    Lu, Guangyuan
    Wang, Feng
    Sun, Tao
    [J]. FRONTIERS IN NEUROLOGY, 2022, 13
  • [7] To what extent a crystal can be superheated
    Jin, ZH
    Lu, K
    [J]. NANOSTRUCTURED MATERIALS, 1999, 12 (1-4): : 369 - 372
  • [8] To What Extent Can We Integrate?
    Ellsworth, Ralph E.
    [J]. COLLEGE & RESEARCH LIBRARIES, 1947, 8 (04): : 401 - 404
  • [9] To what extent can the Future be planned?
    Radbruch, Lukas
    Jaspers, Birgit
    [J]. THERAPEUTISCHE UMSCHAU, 2022, 79 (01) : 1 - 2
  • [10] THE IMPACT OF THE SIMULATION USER ON SIMULATION RESULTS: TO WHAT EXTENT HUMAN THINKING CAN BE REPLACED BY ALGORITHMS?
    Neumann, Gaby
    Tolujew, Juni
    [J]. 22ND EUROPEAN MODELING AND SIMULATION SYMPOSIUM (EMSS 2010), 2010, : 309 - 314