LS-CMA-ES: a Second-order algorithm for Covariance Matrix Adaptation - Archive ouverte HAL Access content directly
Conference Papers Year :

LS-CMA-ES: a Second-order algorithm for Covariance Matrix Adaptation

(1) , (1) , (2)
Anne Auger
  • Function : Author
  • PersonId : 751513
  • IdHAL : anne-auger
Marc Schoenauer


Evolution Strategies, Evolutionary Algorithms based on Gaussian mutation and deterministic selection, are today considered the best choice as far as parameter optimization is concerned. However, there are multiple ways to tune the covariance matrix of the Gaussian mutation. After reviewing the state of the art in covariance matrix adaptation, a new approach is proposed, in which the covariance matrix adaptation method is based on a quadratic approximation of the target function obtained by some Least-Square minimization. A dynamic criterion is designed to detect situations where the approximation is not accurate enough, and original Covariance Matrix Adaptation (CMA) should rather be directly used. The resulting algorithm is experimentally validated on benchmark functions, performing much better than CMA-ES on a large class of problems.
Fichier principal
Vignette du fichier
ppsnANM926.pdf (621.63 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02987505 , version 1 (03-11-2020)


  • HAL Id : hal-02987505 , version 1


Anne Auger, Marc Schoenauer, Nicolas Vanhaecke. LS-CMA-ES: a Second-order algorithm for Covariance Matrix Adaptation. PPSN VIII - 8th International Conference on Parallel Problem Solving from Nature, Sep 2004, Birmingham, United Kingdom. pp.182-191. ⟨hal-02987505⟩
27 View
139 Download


Gmail Facebook Twitter LinkedIn More