Algorithm configuration using GPU-based metaheuristics

Roberto Ugolotti, Youssef S G Nashed, Pablo Mesejo, Stefano Cagnoni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

In this paper, a GPU-based implementation of Differential Evolution (DE) and Particle Swarm Optimization (PSO) in CUDA is used to automatically tune the parameters of PSO. The parameters were tuned over a set of 8 problems and then tested over 20 problems to assess the generalization ability of the tuners. We compare the results obtained using such parameters with the 'standard' ones proposed in the literature and the ones obtained by state-of-the-art tuning methods (irace). The results are comparable to the ones suggested for the standard version of PSO (SPSO), and the ones obtained by irace, while the GPU implementation makes tuning time acceptable. To the best of our knowledge, this is the first time that a general purpose library of GPU-based metaheuristics is used to solve this problem, as well as being one of the few cases where DE and PSO are both used as tuners.

Original languageEnglish (US)
Title of host publicationGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion
Pages221-222
Number of pages2
DOIs
StatePublished - 2013
Event15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013 - Amsterdam, Netherlands
Duration: Jul 6 2013Jul 10 2013

Publication series

NameGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion

Other

Other15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013
CountryNetherlands
CityAmsterdam
Period7/6/137/10/13

Keywords

  • Automatic parameter configuration
  • Evolutionary algorithm
  • GPGPU programming
  • Parallel computing
  • Swarm intelligence

ASJC Scopus subject areas

  • Computational Mathematics

Fingerprint Dive into the research topics of 'Algorithm configuration using GPU-based metaheuristics'. Together they form a unique fingerprint.

Cite this