Analysis of Linear Convergence of a (1 + 1)-ES with Augmented Lagrangian Constraint Handling - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Analysis of Linear Convergence of a (1 + 1)-ES with Augmented Lagrangian Constraint Handling

Asma Atamna
  • Fonction : Auteur
  • PersonId : 736387
  • IdHAL : asma-atamna
Anne Auger
  • Fonction : Auteur
  • PersonId : 751513
  • IdHAL : anne-auger
Nikolaus Hansen

Résumé

We address the question of linear convergence of evolution strategies on constrained optimization problems. In particular, we analyze a (1 + 1)-ES with an augmented Lagrangian constraint handling approach on functions defined on a continuous domain, subject to a single linear inequality constraint. We identify a class of functions for which it is possible to construct a homogeneous Markov chain whose stability implies linear convergence. This class includes all functions such that the augmented Lagrangian of the problem, centered with respect to its value at the optimum and the corresponding Lagrange multiplier, is positive homogeneous of degree 2 (thus including convex quadratic functions as a particular case). The stability of the constructed Markov chain is empirically investigated on the sphere function and on a moderately ill-conditioned ellipsoid function.
Fichier principal
Vignette du fichier
GECCO-2016.pdf (1.08 Mo) Télécharger le fichier
Origine : Accord explicite pour ce dépôt
Loading...

Dates et versions

hal-01318807 , version 1 (20-05-2016)

Identifiants

  • HAL Id : hal-01318807 , version 1

Citer

Asma Atamna, Anne Auger, Nikolaus Hansen. Analysis of Linear Convergence of a (1 + 1)-ES with Augmented Lagrangian Constraint Handling. GECCO 2016 - Genetic and Evolutionary Computation Conference, Jul 2016, Denver, United States. pp.213-220. ⟨hal-01318807⟩
271 Consultations
293 Téléchargements

Partager

Gmail Facebook X LinkedIn More