Cumulative Step-size Adaptation on Linear Functions - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Cumulative Step-size Adaptation on Linear Functions

Abstract

The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies the CSA-ES on composites of strictly increasing functions with affine linear functions through the investigation of its underlying Markov chains. Rigorous results on the change and the variation of the step size are derived with and without cumulation. The step-size diverges geometrically fast in most cases. Furthermore, the influence of the cumulation parameter is studied.
Fichier principal
Vignette du fichier
cumulationonlinearfunctionppsn.pdf (361.41 Ko) Télécharger le fichier
chotard2012postercumulative.pdf (768.94 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other

Dates and versions

hal-00759577 , version 1 (01-12-2012)

Identifiers

Cite

Alexandre Chotard, Anne Auger, Nikolaus Hansen. Cumulative Step-size Adaptation on Linear Functions. PPSN 2012 - 12th International Conference on Parallel Problem Solving From Nature, Sep 2012, Taormina, Italy. pp.72-81. ⟨hal-00759577⟩
162 View
157 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More