Skip to main navigation Skip to search Skip to main content

Permuted orthogonal block-diagonal transformation matrices for large scale optimization benchmarking

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

Abstract

We propose a general methodology to construct large-scale testbeds for the benchmarking of continuous optimization algorithms. Our approach applies an orthogonal transformation on raw functions that involve only a linear number of operations in order to obtain large scale optimization benchmark problems. The orthogonal transformation is sampled from a parametrized family of transformations that are the product of a permutation matrix times a block-diagonal matrix times a permutation matrix. We investigate the impact of the different parameters of the transformation on its shape and on the difficulty of the problems for separable CMA-ES. We illustrate the use of the above defined transformation in the BBOB-2009 testbed as replacement for the expensive orthogonal (rotation) matrices. We also show the practicability of the approach by studying the computational cost and its applicability in a large scale setting.

Original languageEnglish
Title of host publicationGECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference
EditorsTobias Friedrich
PublisherAssociation for Computing Machinery, Inc
Pages189-196
Number of pages8
ISBN (Electronic)9781450342063
DOIs
Publication statusPublished - 20 Jul 2016
Event2016 Genetic and Evolutionary Computation Conference, GECCO 2016 - Denver, United States
Duration: 20 Jul 201624 Jul 2016

Publication series

NameGECCO 2016 - Proceedings of the 2016 Genetic and Evolutionary Computation Conference

Conference

Conference2016 Genetic and Evolutionary Computation Conference, GECCO 2016
Country/TerritoryUnited States
CityDenver
Period20/07/1624/07/16

Keywords

  • Benchmarking
  • Continuous optimization
  • Large scale optimization

Fingerprint

Dive into the research topics of 'Permuted orthogonal block-diagonal transformation matrices for large scale optimization benchmarking'. Together they form a unique fingerprint.

Cite this