Scalarization versus indicator-based selection in multi-objective CMA evolution strategies

Thomas Voß, Nicola Beume, Günter Rudolph, Christian Igel

Abstract

While scalarization approaches to multi- criteria optimization become infeasible in the case of many objectives, for few objectives the benefits of population- based methods compared to a set of independent single- objective optimization trials on scalarized functions are not obvious. The multi-objective covariance matrix adaptation evolution strategy (MO-CMA-ES) is a powerful algorithm for real-valued multi-criteria optimization. This population- based approach combines mutation and strategy adaptation from the elitist CMA-ES with multi-objective selection. We empirically compare the steady-state MO-CMA-ES with different scalarization algorithms, in which the elitist CMA-ES is used as single-objective optimizer. Although only bicriteria benchmark problems are considered, the MO-CMA-ES performs best in the overall comparison. However, if the scalarized problems have a structure that can easily be exploited by the CMA-ES and that is less apparent in the vector-valued fitness function, the CMA- ES with scalarization outperforms the population-based approach.
BibTeX
@inproceedings{vo2008scalarization,
  author = {Thomas Voß and Nicola Beume and Günter Rudolph and Christian Igel},
  title = {{Scalarization versus indicator-based selection in multi-objective CMA evolution strategies}},
  booktitle = {IEEE CEC},
  year = {2008},
  doi = {10.1109/cec.2008.4631208},
}

Loading related content...

Figure