Evolution Strategies with Additive Noise: A Convergence Rate Lower Bound - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Evolution Strategies with Additive Noise: A Convergence Rate Lower Bound

Abstract

We consider the problem of optimizing functions corrupted with additive noise. It is known that evolutionary algo-rithms can reach a simple regret O(1/ √ n) within logarith-mic factors, when n is the number of function evaluations. We show mathematically that this bound is tight, at least for a wide family of evolution strategies without large mutations.
Fichier principal
Vignette du fichier
foga10.pdf (566.13 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01077625 , version 1 (26-10-2014)
hal-01077625 , version 2 (14-04-2015)

Identifiers

  • HAL Id : hal-01077625 , version 2

Cite

Sandra Astete-Morales, Marie-Liesse Cauwet, Olivier Teytaud. Evolution Strategies with Additive Noise: A Convergence Rate Lower Bound. Foundations of Genetic Algorithms, 2015, Aberythswyth, United Kingdom. pp.76--84. ⟨hal-01077625v2⟩
346 View
639 Download

Share

Gmail Facebook Twitter LinkedIn More