Parallelized bayesian optimization for problems with expensive evaluation functions

Margarita Rebolledo, Frederik Rehbach, A. E. Eiben, Thomas Bartz-Beielstein

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

17 Downloads (Pure)


Many black-box optimization problems rely on simulations to evaluate the quality of candidate solutions. These evaluations can be computationally expensive and very time-consuming. We present and approach to mitigate this problem by taking into consideration two factors: The number of evaluations and the execution time. We aim to keep the number of evaluations low by using Bayesian optimization (BO) - known to be sample efficient - and to reduce wall-clock times by executing parallel evaluations. Four parallelization methods using BO as optimizer are compared against the inherently parallel CMA-ES. Each method is evaluated on all the 24 objective functions of the Black-Box-Optimization-Benchmarking test suite in their 20-dimensional versions. The results show that parallelized BO outperforms the state-of-the-art CMA-ES on most of the test functions, also on higher dimensions.

Original languageEnglish
Title of host publicationGECCO '20
Subtitle of host publicationProceedings of the 2020 Genetic and Evolutionary Computation Conference Companion
PublisherAssociation for Computing Machinery, Inc
Number of pages2
ISBN (Electronic)9781450371278
Publication statusPublished - Jul 2020
Event2020 Genetic and Evolutionary Computation Conference, GECCO 2020 - Cancun, Mexico
Duration: 8 Jul 202012 Jul 2020


Conference2020 Genetic and Evolutionary Computation Conference, GECCO 2020


  • Bayesian optimization
  • BBOB
  • Parallel optimization


Dive into the research topics of 'Parallelized bayesian optimization for problems with expensive evaluation functions'. Together they form a unique fingerprint.

Cite this