Maximum Likelihood-based Online Adaptation of Hyper-parameters in CMA-ES
This is an incremental improvement for users of CMA-ES in derivative-free optimization, enhancing performance with non-default settings.
The paper tackled the problem of suboptimal hyper-parameter settings in CMA-ES for larger population sizes by proposing self-CMA-ES for online adaptation, resulting in dynamically approaching optimal settings as shown in experiments.
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.