Log-linear Convergence and Optimal Bounds for the $(1+1)$-ES - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Log-linear Convergence and Optimal Bounds for the $(1+1)$-ES

Mohamed Jebalia
  • Function : Author
  • PersonId : 842777
Anne Auger
  • Function : Author
  • PersonId : 751513
  • IdHAL : anne-auger


The $(1+1)$-ES is modeled by a general stochastic process whose asymptotic behavior is investigated. Under general assumptions, it is shown that the convergence of the related algorithm is sub-log-linear, bounded below by an explicit log-linear rate. For the specific case of spherical functions and scale-invariant algorithm, it is proved using the Law of Large Numbers for orthogonal variables, that the linear convergence holds almost surely and that the best convergence rate is reached. Experimental simulations illustrate the theoretical results.
Fichier principal
Vignette du fichier
AJL_EA07WithErrata.pdf (325.06 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00173483 , version 1 (19-09-2007)
inria-00173483 , version 2 (05-10-2007)
inria-00173483 , version 3 (03-07-2008)
inria-00173483 , version 4 (03-07-2008)



Mohamed Jebalia, Anne Auger, Pierre Liardet. Log-linear Convergence and Optimal Bounds for the $(1+1)$-ES. Evolution Artificielle, Oct 2007, Tours, France. pp.207-218, ⟨10.1007/978-3-540-79305-2⟩. ⟨inria-00173483v4⟩
283 View
483 Download



Gmail Facebook Twitter LinkedIn More