 |
 |
|
|
| inria-00173483, version 4 |
 |
|
|
|
| See detailed view |  BibTeX EndNote TEI RefWorks |
|
|
|||||||
| Evolution Artificielle 4926/2008 (2007) 207-218 |
| Link to full text from publisher |
|
| 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. |
|
|
|
|
|
|
|
|
|
| a – | |
| 1: | TAO (INRIA Futurs) |
|
INRIA – CNRS : UMR8623 – Université Paris Sud - Paris XI |
| 2: | Centre de Mathématiques et Informatique (CMI) |
|
Université de Provence - Aix-Marseille I |
|
|
|
|
|
|
|
|
|
| Domain | : | Computer Science/Numerical Analysis |
| 10.1007/978-3-540-79305-2 |
|
| Available versions: | v1 (2007-09-20) | v2 (2007-10-05) | v3 (2008-07-03) | v4 (2008-07-03) |
| inria-00173483, version 4 | |
| http://hal.inria.fr/inria-00173483/en/ | |
| oai:hal.inria.fr:inria-00173483_v4 | |
| From: Anne Auger | |
| Submitted on: Thursday, 3 July 2008 14:30:27 | |
| Updated on: Thursday, 3 July 2008 21:48:38 | |
