On multiplicative noise models for stochastic search

Mohamed Jebalia 1 Anne Auger 1
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : In this paper we investigate multiplicative noise models in the context of continuous optimization. We illustrate how some intrinsic properties of the noise model imply the failure of reasonable search algorithms for locating the optimum of the noiseless part of the objective function. Those findings are rigorously investigated on the (1+1)-ES for the minimization of the noisy sphere function. Assuming a lower bound on the support of the noise distribution, we prove that the (1+1)-ES diverges when the lower bound allows to sample negative fitness with positive probability and converges in the opposite case. We provide a discussion on the practical applications and non applications of those outcomes and explain the differences with previous results obtained in the limit of infinite search-space dimensionality.
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/inria-00287725
Contributor : Mohamed Jebalia <>
Submitted on : Monday, August 18, 2008 - 3:51:17 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Friday, September 28, 2012 - 3:52:31 PM

File

MohamedAnnePPSN08.ForHal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00287725, version 1

Collections

Citation

Mohamed Jebalia, Anne Auger. On multiplicative noise models for stochastic search. Parallel Problem Solving From Nature, Sep 2008, dortmund, Germany. ⟨inria-00287725⟩

Share

Metrics

Record views

553

Files downloads

209