Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions

(1, 2) , (1, 2)
1
2

Abstract

We study the linear convergence of a simple evolutionary algorithm on non quasi-convex functions on continuous domains. Assumptions include an assumption on the sampling performed by the evolutionary algorithm (supposed to cover efficiently the neighborhood of the current search point), the conditioning of the objective function (so that the probability of improvement is not too low at each time step, given a correct step size), and the unicity of the optimum.
Fichier principal
Vignette du fichier
linearConvergence.pdf (520.25 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00907671 , version 1 (21-11-2013)

Identifiers

  • HAL Id : hal-00907671 , version 1

Cite

Jérémie Decock, Olivier Teytaud. Linear Convergence of Evolution Strategies with Derandomized Sampling Beyond Quasi-Convex Functions. EA - 11th Biennal International Conference on Artificial Evolution - 2013, Oct 2013, Bordeaux, France. ⟨hal-00907671⟩
176 View
134 Download

Share

Gmail Facebook Twitter LinkedIn More