Principled Design of Continuous Stochastic Search: From Theory to Practice

Nikolaus Hansen 1 Anne Auger 1
1 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : We derive a stochastic search procedure for parameter optimization from two first principles: (1) imposing the least prior assumptions, namely by maximum entropy sampling, unbiasedness and invariance; (2) exploiting all available information under the constraints imposed by (1). We additionally require that two of the most basic functions can be solved reasonably fast. Given these principles, two principal heuristics are used: reinforcing of good solutions and good steps (increasing their likelihood) and rendering successive steps orthogonal. The resulting search algorithm is the covariance matrix adaptation evolution strategy, CMA-ES that coincides to a great extend to a natural gradient descent. The invariance properties of the CMA-ES are formalized, as well as its maximum likelihood and stationarity properties. A small parameter study for a specific heuristic--deduced from the principles of reinforcing good steps and exploiting all information--is presented, namely for the cumulation of an evolution or search path. Experiments on two noisy functions are provided.
Document type :
Book sections
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download
https://hal.inria.fr/hal-00808450
Contributor : Nikolaus Hansen <>
Submitted on : Sunday, July 27, 2014 - 2:36:22 PM
Last modification on : Sunday, July 21, 2019 - 1:48:05 AM
Long-term archiving on : Tuesday, April 11, 2017 - 6:24:58 PM

File

hansen2013principled.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00808450, version 3

Collections

INRIA | UMR8623 | LRI-AO

Citation

Nikolaus Hansen, Anne Auger. Principled Design of Continuous Stochastic Search: From Theory to Practice. Yossi Borenstein and Alberto Moraglio. Theory and Principled Methods for the Design of Metaheuristics, Springer, pp.145-180, 2014, Natural Computing Series, 978-3-642-33205-0. ⟨hal-00808450v3⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

733

Files downloads

577

Contact


archive-ouverte@inria.fr