Investigating the Impact of Sequential Selection in the (1,2)-CMA-ES on the Noiseless BBOB-2010 Testbed - Archive ouverte HAL
Conference Papers Year : 2010

Investigating the Impact of Sequential Selection in the (1,2)-CMA-ES on the Noiseless BBOB-2010 Testbed

Anne Auger
  • Function : Author
  • PersonId : 751513
  • IdHAL : anne-auger
Nikolaus Hansen

Abstract

This paper investigates the impact of sequential selection, a concept recently introduced for Evolution Strategies (ESs), that consists in performing the evaluations of the different candidate solutions sequentially, concluding the iteration immediately if one offspring is better than the parent. The performance of the (1,2)-Covariance-Matrix-Adaptation Evolution-Strategy (CMA-ES) is compared to the performance of the (1,2$^s$)-CMA-ES where sequential selection is implemented on the BBOB-2010 noiseless benchmark testbed. For each strategy, an independent restart mechanism is implemented. A total budget of $10^{4} D$ function evaluations per trial has been used, where $D$ is the dimension of the search space. The experiments do not allow a general statement regarding a statistically significant difference between the two algorithms and we conclude that the sequential selection has no impact on the performance of the (1,2)-CMA-ES on the noiseless BBOB-2009 testbed.
Fichier principal
Vignette du fichier
ws1p22-augerAuthorVersion.pdf (1.48 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

inria-00502431 , version 1 (14-07-2010)

Identifiers

Cite

Anne Auger, Dimo Brockhoff, Nikolaus Hansen. Investigating the Impact of Sequential Selection in the (1,2)-CMA-ES on the Noiseless BBOB-2010 Testbed. GECCO workshop on Black-Box Optimization Benchmarking (BBOB'2010), Jul 2010, Portland, OR, United States. pp.1591-1596, ⟨10.1145/1830761.1830777⟩. ⟨inria-00502431⟩
113 View
215 Download

Altmetric

Share

More