Skip to Main content Skip to Navigation
Conference papers

Algorithm configuration using GPU-based metaheuristics

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.
Complete list of metadata

Cited literature [5 references]  Display  Hide  Download
Contributor : Pablo Mesejo Santiago Connect in order to contact the contributor
Submitted on : Wednesday, October 28, 2015 - 11:35:12 AM
Last modification on : Thursday, October 29, 2015 - 1:08:55 AM
Long-term archiving on: : Friday, January 29, 2016 - 1:15:40 PM


Files produced by the author(s)




Roberto Ugolotti, Youssef S.G. Nashed, Pablo Mesejo, Stefano Cagnoni. Algorithm configuration using GPU-based metaheuristics. 15th Genetic and Evolutionary Computation Conference companion (GECCO’13), Jul 2013, Amsterdam, Netherlands. pp.221-222, ⟨10.1145/2464576.2464682⟩. ⟨hal-01221570⟩



Record views


Files downloads