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

Nikolaus Hansen 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 : 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.
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-01110313
Contributor : Nikolaus Hansen <>
Submitted on : Thursday, January 29, 2015 - 8:05:56 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Wednesday, May 27, 2015 - 1:41:48 PM

File

hansen-pgmo-copi-2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01110313, version 1

Collections

Citation

Nikolaus Hansen. CMA-ES: A Function Value Free Second Order Optimization Method. PGMO COPI 2014, Oct 2014, Paris, France. 2014. ⟨hal-01110313⟩

Share

Metrics

Record views

574

Files downloads

432