Recombination for learning strategy parameters in the MO-CMA-ES
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Recombination for learning strategy parameters in the MO-CMA-ES. / Voß, Thomas; Hansen, Nikolaus; Igel, Christian.
Evolutionary Multi-Criterion Optimization: 5th International Conference, EMO 2009, Nantes, France, April 7-10, 2009. Proceedings. ed. / Matthias Ehrgott; Carlos M. Fonseca; Xavier Gandibleux; Jin-Kao Hao; Marc Sevaux. Springer, 2009. p. 155-168 (Lecture notes in computer science, Vol. 5467).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Recombination for learning strategy parameters in the MO-CMA-ES
AU - Voß, Thomas
AU - Hansen, Nikolaus
AU - Igel, Christian
PY - 2009
Y1 - 2009
N2 - The multi-objective covariance matrix adaptation evolution strategy (MO-CMA-ES) is a variable-metric algorithm for real-valued vector optimization. It maintains a parent population of candidate solutions, which are varied by additive, zero-mean Gaussian mutations. Each individual learns its own covariance matrix for the mutation distribution considering only its parent and offspring. However, the optimal mutation distribution of individuals that are close in decision space are likely to be similar if we presume some notion of continuity of the optimization problem. Therefore, we propose a lateral (inter-individual) transfer of information in the MO-CMA-ES considering also successful mutations of neighboring individuals for the covariance matrix adaptation. We evaluate this idea on common bi-criteria objective functions. The preliminary results show that the new adaptation rule significantly improves the performance of the MO-CMA-ES.
AB - The multi-objective covariance matrix adaptation evolution strategy (MO-CMA-ES) is a variable-metric algorithm for real-valued vector optimization. It maintains a parent population of candidate solutions, which are varied by additive, zero-mean Gaussian mutations. Each individual learns its own covariance matrix for the mutation distribution considering only its parent and offspring. However, the optimal mutation distribution of individuals that are close in decision space are likely to be similar if we presume some notion of continuity of the optimization problem. Therefore, we propose a lateral (inter-individual) transfer of information in the MO-CMA-ES considering also successful mutations of neighboring individuals for the covariance matrix adaptation. We evaluate this idea on common bi-criteria objective functions. The preliminary results show that the new adaptation rule significantly improves the performance of the MO-CMA-ES.
U2 - 10.1007/978-3-642-01020-0_16
DO - 10.1007/978-3-642-01020-0_16
M3 - Article in proceedings
AN - SCOPUS:78650751826
SN - 978-3-642-01019-4
T3 - Lecture notes in computer science
SP - 155
EP - 168
BT - Evolutionary Multi-Criterion Optimization
A2 - Ehrgott, Matthias
A2 - Fonseca, Carlos M.
A2 - Gandibleux, Xavier
A2 - Hao, Jin-Kao
A2 - Sevaux, Marc
PB - Springer
T2 - 5th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2009
Y2 - 7 April 2009 through 10 April 2009
ER -
ID: 168462009