Unbounded population MO-CMA-ES for the bi-objective BBOB test suite

Oswin Krause; Tobias Glasmachers; Nikolaus Hansen; Christian Igel

doi:10.1145/2908961.2931699

Unbounded population MO-CMA-ES for the bi-objective BBOB test suite

Oswin Krause, Tobias Glasmachers, Nikolaus Hansen, Christian Igel

Department of Computer Science

13 Citations (Scopus)

Abstract

The unbounded population multi-objective covariance matrix adaptation evolution strategy∼(UP-MO-CMA-ES) aims at maximizing the total hypervolume covered by all evaluated points. It adds all non-dominated solutions found to its population and employs Gaussian mutations with adaptive covariance matrices to also solve ill-conditioned problems. A novel recombination operator adapts the covariance matrices to point along the Pareto front. The UP-MO-CMA-ES is combined with a parallel exploration strategy and empirically evaluated on the bi-objective BBOB-biobj benchmark problems. Results show that the algorithm can reliably solve ill-conditioned problems as well as weakly-structured problems. However, it is less suited for the rugged multi-modal objective functions in the benchmark.

Original language	English
Title of host publication	Proceedings of the 2016 Genetic and Evolutionary Computation Conference Companion
Number of pages	8
Publisher	Association for Computing Machinery
Publication date	20 Jul 2016
Pages	1177-1184
ISBN (Print)	978-1-4503-4323-7
DOIs	https://doi.org/10.1145/2908961.2931699
Publication status	Published - 20 Jul 2016
Event	Genetic and Evolutionary Computation Conference - Denver, United States Duration: 20 Jul 2016 → 24 Jul 2016

Conference

Conference	Genetic and Evolutionary Computation Conference
Country/Territory	United States
City	Denver
Period	20/07/2016 → 24/07/2016

Access to Document

10.1145/2908961.2931699

Cite this

Unbounded population MO-CMA-ES for the bi-objective BBOB test suite. / Krause, Oswin; Glasmachers, Tobias; Hansen, Nikolaus et al.

Proceedings of the 2016 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, 2016. p. 1177-1184.

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

Krause, O, Glasmachers, T, Hansen, N & Igel, C 2016, Unbounded population MO-CMA-ES for the bi-objective BBOB test suite. in Proceedings of the 2016 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, pp. 1177-1184, Genetic and Evolutionary Computation Conference, Denver, United States, 20/07/2016. https://doi.org/10.1145/2908961.2931699

@inproceedings{093e1d9190b94e35b45ede18516985a6,

title = "Unbounded population MO-CMA-ES for the bi-objective BBOB test suite",

abstract = "The unbounded population multi-objective covariance matrix adaptation evolution strategy∼(UP-MO-CMA-ES) aims at maximizing the total hypervolume covered by all evaluated points. It adds all non-dominated solutions found to its population and employs Gaussian mutations with adaptive covariance matrices to also solve ill-conditioned problems. A novel recombination operator adapts the covariance matrices to point along the Pareto front. The UP-MO-CMA-ES is combined with a parallel exploration strategy and empirically evaluated on the bi-objective BBOB-biobj benchmark problems. Results show that the algorithm can reliably solve ill-conditioned problems as well as weakly-structured problems. However, it is less suited for the rugged multi-modal objective functions in the benchmark.",

author = "Oswin Krause and Tobias Glasmachers and Nikolaus Hansen and Christian Igel",

year = "2016",

month = jul,

day = "20",

doi = "10.1145/2908961.2931699",

language = "English",

isbn = "978-1-4503-4323-7",

pages = "1177--1184",

booktitle = "Proceedings of the 2016 Genetic and Evolutionary Computation Conference Companion",

publisher = "Association for Computing Machinery",

note = "Genetic and Evolutionary Computation Conference ; Conference date: 20-07-2016 Through 24-07-2016",

}

TY - GEN

T1 - Unbounded population MO-CMA-ES for the bi-objective BBOB test suite

AU - Krause, Oswin

AU - Glasmachers, Tobias

AU - Hansen, Nikolaus

AU - Igel, Christian

PY - 2016/7/20

Y1 - 2016/7/20

N2 - The unbounded population multi-objective covariance matrix adaptation evolution strategy∼(UP-MO-CMA-ES) aims at maximizing the total hypervolume covered by all evaluated points. It adds all non-dominated solutions found to its population and employs Gaussian mutations with adaptive covariance matrices to also solve ill-conditioned problems. A novel recombination operator adapts the covariance matrices to point along the Pareto front. The UP-MO-CMA-ES is combined with a parallel exploration strategy and empirically evaluated on the bi-objective BBOB-biobj benchmark problems. Results show that the algorithm can reliably solve ill-conditioned problems as well as weakly-structured problems. However, it is less suited for the rugged multi-modal objective functions in the benchmark.

AB - The unbounded population multi-objective covariance matrix adaptation evolution strategy∼(UP-MO-CMA-ES) aims at maximizing the total hypervolume covered by all evaluated points. It adds all non-dominated solutions found to its population and employs Gaussian mutations with adaptive covariance matrices to also solve ill-conditioned problems. A novel recombination operator adapts the covariance matrices to point along the Pareto front. The UP-MO-CMA-ES is combined with a parallel exploration strategy and empirically evaluated on the bi-objective BBOB-biobj benchmark problems. Results show that the algorithm can reliably solve ill-conditioned problems as well as weakly-structured problems. However, it is less suited for the rugged multi-modal objective functions in the benchmark.

U2 - 10.1145/2908961.2931699

DO - 10.1145/2908961.2931699

M3 - Article in proceedings

SN - 978-1-4503-4323-7

SP - 1177

EP - 1184

BT - Proceedings of the 2016 Genetic and Evolutionary Computation Conference Companion

PB - Association for Computing Machinery

T2 - Genetic and Evolutionary Computation Conference

Y2 - 20 July 2016 through 24 July 2016

ER -

Unbounded population MO-CMA-ES for the bi-objective BBOB test suite

Abstract

Conference

Access to Document

Fingerprint

Cite this