Recombination Weight Based Selection in the DTS-CMA-ES
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Recombination Weight Based Selection in the DTS-CMA-ES. / Krause, Oswin.
Parallel Problem Solving from Nature: PPSN XVII - 17th International Conference, PPSN 2022, Proceedings, Part II. red. / Günter Rudolph; Anna V. Kononova; Hernán Aguirre; Pascal Kerschke; Gabriela Ochoa; Tea Tušar. Springer, 2022. s. 295-308 (Lecture Notes in Computer Science, Bind 13399 LNCS).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Recombination Weight Based Selection in the DTS-CMA-ES
AU - Krause, Oswin
N1 - Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Surrogate model based Evolution Strategies (like the doubly trained surrogate model CMA-ES, DTS-CMA-ES) use a model of the objective function to reduce the number of function evaluations during optimization. This work investigates to use the expected selection weights averaged over the GP posterior distribution as replacement of the fitness and to guide point-selection for evaluation via the variance of the weights. Results obtained on BBOB show that the proposed technique performs on par with current strategies and allows the usage of surrogate models that are invariant to strictly increasing transformations of the function values. However, initial experiments showed that simple modeling of ranks in the GP does lead to worse results than current GP models of the function values.
AB - Surrogate model based Evolution Strategies (like the doubly trained surrogate model CMA-ES, DTS-CMA-ES) use a model of the objective function to reduce the number of function evaluations during optimization. This work investigates to use the expected selection weights averaged over the GP posterior distribution as replacement of the fitness and to guide point-selection for evaluation via the variance of the weights. Results obtained on BBOB show that the proposed technique performs on par with current strategies and allows the usage of surrogate models that are invariant to strictly increasing transformations of the function values. However, initial experiments showed that simple modeling of ranks in the GP does lead to worse results than current GP models of the function values.
KW - CMA-ES
KW - DTS-CMA-ES
KW - Gaussian process
KW - Recombination
KW - Surrogate models
U2 - 10.1007/978-3-031-14721-0_21
DO - 10.1007/978-3-031-14721-0_21
M3 - Article in proceedings
AN - SCOPUS:85137266869
SN - 978-3-031-14720-3
T3 - Lecture Notes in Computer Science
SP - 295
EP - 308
BT - Parallel Problem Solving from Nature
A2 - Rudolph, Günter
A2 - Kononova, Anna V.
A2 - Aguirre, Hernán
A2 - Kerschke, Pascal
A2 - Ochoa, Gabriela
A2 - Tušar, Tea
PB - Springer
T2 - 17th International Conference on Parallel Problem Solving from Nature, PPSN 2022
Y2 - 10 September 2022 through 14 September 2022
ER -
ID: 342669813