Adaptive Coordinate Descent

Ilya Loshchilov 1 Marc Schoenauer 1, 2 Michèle Sebag 1, 2
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 : Independence from the coordinate system is one source of efficiency and robustness for the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). The recently proposed Adaptive Encoding (AE) procedure generalizes CMA-ES adaptive mechanism, and can be used together with any optimization algorithm. Adaptive Encoding gradually builds a transformation of the coordinate system such that the new coordinates are as decorrelated as possible with respect to the objective function. But any optimization algorithm can then be used together with Adaptive Encoding, and this paper proposes to use one of the simplest of all, that uses a dichotomy procedure on each coordinate in turn. The resulting algorithm, termed Adaptive Coordinate Descent (ACiD), is analyzed on the Sphere function, and experimentally validated on BBOB testbench where it is shown to outperform the standard (1 + 1)-CMA-ES, and is found comparable to other state-of-the-art CMA-ES variants.
Document type :
Conference papers
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00587534
Contributor : Loshchilov Ilya <>
Submitted on : Wednesday, April 20, 2011 - 4:18:33 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Thursday, July 21, 2011 - 2:41:33 AM

File

AdaptiveCoordinateDescent.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00587534, version 1

Collections

Citation

Ilya Loshchilov, Marc Schoenauer, Michèle Sebag. Adaptive Coordinate Descent. Genetic and Evolutionary Computation Conference (GECCO 2011), ACM-SIGEVO, Jul 2011, Dublin, Ireland. pp.885-992. ⟨inria-00587534⟩

Share

Metrics

Record views

473

Files downloads

2049