CMA-ES: A Function Value Free Second Order Optimization Method - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

CMA-ES: A Function Value Free Second Order Optimization Method

Abstract

We give a bird's-eye view introduction to the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and emphasize relevant design aspects of the algorithm, namely its invariance properties. While CMA-ES is gradient and function value free, we show that using the gradient in CMA-ES is possible and can reduce the number of iterations on unimodal, smooth functions.
Fichier principal
Vignette du fichier
hansen-pgmo-copi-2014.pdf (451.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01110313 , version 1 (29-01-2015)

Identifiers

  • HAL Id : hal-01110313 , version 1

Cite

Nikolaus Hansen. CMA-ES: A Function Value Free Second Order Optimization Method. PGMO COPI 2014 - Gaspard Monge Program for Optimization and operations research Conference on Optimization and Practices in Industry, Oct 2014, Saclay, France. ⟨hal-01110313⟩
568 View
548 Download

Share

Gmail Facebook X LinkedIn More