English

Maximum Likelihood-based Online Adaptation of Hyper-parameters in CMA-ES

Neural and Evolutionary Computing 2014-06-12 v2 Artificial Intelligence

Abstract

The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is widely accepted as a robust derivative-free continuous optimization algorithm for non-linear and non-convex optimization problems. CMA-ES is well known to be almost parameterless, meaning that only one hyper-parameter, the population size, is proposed to be tuned by the user. In this paper, we propose a principled approach called self-CMA-ES to achieve the online adaptation of CMA-ES hyper-parameters in order to improve its overall performance. Experimental results show that for larger-than-default population size, the default settings of hyper-parameters of CMA-ES are far from being optimal, and that self-CMA-ES allows for dynamically approaching optimal settings.

Keywords

Cite

@article{arxiv.1406.2623,
  title  = {Maximum Likelihood-based Online Adaptation of Hyper-parameters in CMA-ES},
  author = {Ilya Loshchilov and Marc Schoenauer and Michèle Sebag and Nikolaus Hansen},
  journal= {arXiv preprint arXiv:1406.2623},
  year   = {2014}
}

Comments

13th International Conference on Parallel Problem Solving from Nature (PPSN 2014) (2014)

R2 v1 2026-06-22T04:35:16.078Z