-
Something wrong with this record ?
A comparison of global search algorithms for continuous black box optimization
P. Pošík, W. Huyer, L. Pál,
Language English Country United States
Document type Comparative Study, Journal Article, Research Support, Non-U.S. Gov't
PubMed
22708992
DOI
10.1162/evco_a_00084
Knihovny.cz E-resources
- MeSH
- Algorithms * MeSH
- Benchmarking methods MeSH
- Numerical Analysis, Computer-Assisted MeSH
- Models, Theoretical * MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
- Comparative Study MeSH
Four methods for global numerical black box optimization with origins in the mathematical programming community are described and experimentally compared with the state of the art evolutionary method, BIPOP-CMA-ES. The methods chosen for the comparison exhibit various features that are potentially interesting for the evolutionary computation community: systematic sampling of the search space (DIRECT, MCS) possibly combined with a local search method (MCS), or a multi-start approach (NEWUOA, GLOBAL) possibly equipped with a careful selection of points to run a local optimizer from (GLOBAL). The recently proposed "comparing continuous optimizers" (COCO) methodology was adopted as the basis for the comparison. Based on the results, we draw suggestions about which algorithm should be used depending on the available budget of function evaluations, and we propose several possibilities for hybridizing evolutionary algorithms (EAs) with features of the other compared algorithms.
References provided by Crossref.org
- 000
- 00000naa a2200000 a 4500
- 001
- bmc13024405
- 003
- CZ-PrNML
- 005
- 20130708112641.0
- 007
- ta
- 008
- 130703s2012 xxu f 000 0|eng||
- 009
- AR
- 024 7_
- $a 10.1162/EVCO_a_00084 $2 doi
- 035 __
- $a (PubMed)22708992
- 040 __
- $a ABA008 $b cze $d ABA008 $e AACR2
- 041 0_
- $a eng
- 044 __
- $a xxu
- 100 1_
- $a Pošík, Petr $u Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic. posik@labe.felk.cvut.cz
- 245 12
- $a A comparison of global search algorithms for continuous black box optimization / $c P. Pošík, W. Huyer, L. Pál,
- 520 9_
- $a Four methods for global numerical black box optimization with origins in the mathematical programming community are described and experimentally compared with the state of the art evolutionary method, BIPOP-CMA-ES. The methods chosen for the comparison exhibit various features that are potentially interesting for the evolutionary computation community: systematic sampling of the search space (DIRECT, MCS) possibly combined with a local search method (MCS), or a multi-start approach (NEWUOA, GLOBAL) possibly equipped with a careful selection of points to run a local optimizer from (GLOBAL). The recently proposed "comparing continuous optimizers" (COCO) methodology was adopted as the basis for the comparison. Based on the results, we draw suggestions about which algorithm should be used depending on the available budget of function evaluations, and we propose several possibilities for hybridizing evolutionary algorithms (EAs) with features of the other compared algorithms.
- 650 12
- $a algoritmy $7 D000465
- 650 _2
- $a benchmarking $x metody $7 D019985
- 650 12
- $a teoretické modely $7 D008962
- 650 _2
- $a numerická analýza pomocí počítače $7 D009716
- 655 _2
- $a srovnávací studie $7 D003160
- 655 _2
- $a časopisecké články $7 D016428
- 655 _2
- $a práce podpořená grantem $7 D013485
- 700 1_
- $a Huyer, Waltraud $u -
- 700 1_
- $a Pál, László $u -
- 773 0_
- $w MED00007225 $t Evolutionary computation $x 1530-9304 $g Roč. 20, č. 4 (2012), s. 509-41
- 856 41
- $u https://pubmed.ncbi.nlm.nih.gov/22708992 $y Pubmed
- 910 __
- $a ABA008 $b sig $c sign $y a $z 0
- 990 __
- $a 20130703 $b ABA008
- 991 __
- $a 20130708113102 $b ABA008
- 999 __
- $a ok $b bmc $g 988085 $s 822785
- BAS __
- $a 3
- BAS __
- $a PreBMC
- BMC __
- $a 2012 $b 20 $c 4 $d 509-41 $i 1530-9304 $m Evolutionary computation $n Evol Comput $x MED00007225
- LZP __
- $a Pubmed-20130703
