Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed

Nikolaus Hansen; Raymond Ros

doi:10.1145/1830761.1830768

Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed

Nikolaus Hansen
, Raymond Ros

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, the performances of the NEW Unconstrained Optimization Algorithm (NEWUOA) on some noiseless functions are compared to those of the BI-POPulation Covariance Matrix Adaptation-Evolution Strategy (BIPOP-CMA-ES). The two algorithms were benchmarked on the BBOB 2009 noiseless function testbed. The comparison shows that NEWUOA outperforms BIPOP-CMA-ES on some functions like the Sphere or the Rosenbrock functions. Also the independent restart procedure used for NEWUOA allows it to perform better than BIPOP-CMA-ES on the Gallagher functions. Nevertheless, BIPOP-CMA-ES is faster and has a better success probability than NEWUOA in reaching target function values smaller than one on all other functions.

Original language	English
Title of host publication	Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication
Pages	1519-1526
Number of pages	8
DOIs	https://doi.org/10.1145/1830761.1830768
Publication status	Published - 30 Aug 2010
Externally published	Yes
Event	12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010 - Portland, OR, United States Duration: 7 Jul 2010 → 11 Jul 2010

Publication series

Name	Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication

Conference

Conference	12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010
Country/Territory	United States
City	Portland, OR
Period	7/07/10 → 11/07/10

Keywords

Benchmarking
Black-box optimization
Derivative-free optimization
Evolution strategy

Access to Document

10.1145/1830761.1830768

Cite this

Hansen, N., & Ros, R. (2010). Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed. In Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication (pp. 1519-1526). (Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication). https://doi.org/10.1145/1830761.1830768

Hansen, Nikolaus ; Ros, Raymond. / Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES : On the BBOB noiseless testbed. Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication. 2010. pp. 1519-1526 (Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication).

@inproceedings{14f95d791ef8412eb35a3691160fba18,

title = "Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed",

abstract = "In this paper, the performances of the NEW Unconstrained Optimization Algorithm (NEWUOA) on some noiseless functions are compared to those of the BI-POPulation Covariance Matrix Adaptation-Evolution Strategy (BIPOP-CMA-ES). The two algorithms were benchmarked on the BBOB 2009 noiseless function testbed. The comparison shows that NEWUOA outperforms BIPOP-CMA-ES on some functions like the Sphere or the Rosenbrock functions. Also the independent restart procedure used for NEWUOA allows it to perform better than BIPOP-CMA-ES on the Gallagher functions. Nevertheless, BIPOP-CMA-ES is faster and has a better success probability than NEWUOA in reaching target function values smaller than one on all other functions.",

keywords = "Benchmarking, Black-box optimization, Derivative-free optimization, Evolution strategy",

author = "Nikolaus Hansen and Raymond Ros",

year = "2010",

month = aug,

day = "30",

doi = "10.1145/1830761.1830768",

language = "English",

isbn = "9781450300735",

series = "Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication",

pages = "1519--1526",

booktitle = "Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication",

note = "12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010 ; Conference date: 07-07-2010 Through 11-07-2010",

}

Hansen, N & Ros, R 2010, Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed. in Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication. Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication, pp. 1519-1526, 12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010, Portland, OR, United States, 7/07/10. https://doi.org/10.1145/1830761.1830768

Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed. / Hansen, Nikolaus; Ros, Raymond.
Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication. 2010. p. 1519-1526 (Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES

T2 - 12th Annual Genetic and Evolutionary Computation Conference, GECCO-2010

AU - Hansen, Nikolaus

AU - Ros, Raymond

PY - 2010/8/30

Y1 - 2010/8/30

N2 - In this paper, the performances of the NEW Unconstrained Optimization Algorithm (NEWUOA) on some noiseless functions are compared to those of the BI-POPulation Covariance Matrix Adaptation-Evolution Strategy (BIPOP-CMA-ES). The two algorithms were benchmarked on the BBOB 2009 noiseless function testbed. The comparison shows that NEWUOA outperforms BIPOP-CMA-ES on some functions like the Sphere or the Rosenbrock functions. Also the independent restart procedure used for NEWUOA allows it to perform better than BIPOP-CMA-ES on the Gallagher functions. Nevertheless, BIPOP-CMA-ES is faster and has a better success probability than NEWUOA in reaching target function values smaller than one on all other functions.

AB - In this paper, the performances of the NEW Unconstrained Optimization Algorithm (NEWUOA) on some noiseless functions are compared to those of the BI-POPulation Covariance Matrix Adaptation-Evolution Strategy (BIPOP-CMA-ES). The two algorithms were benchmarked on the BBOB 2009 noiseless function testbed. The comparison shows that NEWUOA outperforms BIPOP-CMA-ES on some functions like the Sphere or the Rosenbrock functions. Also the independent restart procedure used for NEWUOA allows it to perform better than BIPOP-CMA-ES on the Gallagher functions. Nevertheless, BIPOP-CMA-ES is faster and has a better success probability than NEWUOA in reaching target function values smaller than one on all other functions.

KW - Benchmarking

KW - Black-box optimization

KW - Derivative-free optimization

KW - Evolution strategy

UR - https://www.scopus.com/pages/publications/77955973983

U2 - 10.1145/1830761.1830768

DO - 10.1145/1830761.1830768

M3 - Conference contribution

AN - SCOPUS:77955973983

SN - 9781450300735

T3 - Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication

SP - 1519

EP - 1526

BT - Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication

Y2 - 7 July 2010 through 11 July 2010

ER -

Hansen N, Ros R. Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed. In Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication. 2010. p. 1519-1526. (Proceedings of the 12th Annual Genetic and Evolutionary Computation Conference, GECCO '10 - Companion Publication). doi: 10.1145/1830761.1830768

Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES: On the BBOB noiseless testbed

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this