FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312948503> ?p ?o ?g. }

• W4312948503 endingPage "1526" @default.
• W4312948503 startingPage "1511" @default.
• W4312948503 abstract "The performance of an evolutionary algorithm (EA) is deeply affected by its control parameter's setting. It has become a trend in recent studies to treat the control parameter as a random variable. In these studies, the associated distribution of the control parameter is updated at each generation and new parameter setting is sampled from the distribution. The distribution's parameter (called hyper-parameter) is thus critical to the algorithmic performance. In this paper, we propose a variational learning framework to tune the hyper-parameters of EA, in which the expectation-maximization (EM) algorithm and a reinforcement learning algorithm are combined. To verify the effectiveness of the proposed method which is named Reinforcement EM (REM), we apply it to tune the hyper-parameters of the distributions of two important parameters, i.e. the scaling parameter ( <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$F$</tex-math></inline-formula> ) and crossover rate ( <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$CR$</tex-math></inline-formula> ), of differential evolution (DE) and an adaptive DE algorithm. In addition, we propose to use the meta-learning technique to learn good initial distributions for the hyper-parameters of <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$F$</tex-math></inline-formula> and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$CR$</tex-math></inline-formula> so that the REM can effectively adapt to a new optimization problem. Experimental results obtained on the CEC 2018 test suite show that with the tuned hyper-parameters, DE and the adaptive DE can achieve significantly better performance than their counterparts with empirical parameter settings and with parameters tuned by some widely-used tuning methods, including ParamILS, F-Race and Bayesian optimization algorithm." @default.
• W4312948503 created "2023-01-05" @default.
• W4312948503 creator A5005474942 @default.
• W4312948503 creator A5043861652 @default.
• W4312948503 creator A5057345644 @default.
• W4312948503 creator A5060123829 @default.
• W4312948503 creator A5075938156 @default.
• W4312948503 date "2023-10-01" @default.
• W4312948503 modified "2023-10-11" @default.
• W4312948503 title "Variational Reinforcement Learning for Hyper-Parameter Tuning of Adaptive Evolutionary Algorithm" @default.
• W4312948503 cites W1977026564 @default.
• W4312948503 cites W2010861271 @default.
• W4312948503 cites W2042253843 @default.
• W4312948503 cites W2047229728 @default.
• W4312948503 cites W2052367557 @default.
• W4312948503 cites W2123066915 @default.
• W4312948503 cites W2134154181 @default.
• W4312948503 cites W2137340504 @default.
• W4312948503 cites W2143983955 @default.
• W4312948503 cites W2155529731 @default.
• W4312948503 cites W2156194072 @default.
• W4312948503 cites W2162145193 @default.
• W4312948503 cites W2200000192 @default.
• W4312948503 cites W2257979135 @default.
• W4312948503 cites W2334782222 @default.
• W4312948503 cites W2507221917 @default.
• W4312948503 cites W2557488584 @default.
• W4312948503 cites W2558097110 @default.
• W4312948503 cites W2891186800 @default.
• W4312948503 cites W2902454235 @default.
• W4312948503 cites W2903569983 @default.
• W4312948503 cites W2914049157 @default.
• W4312948503 cites W2950680102 @default.
• W4312948503 cites W2961614712 @default.
• W4312948503 cites W2963862287 @default.
• W4312948503 cites W2968187932 @default.
• W4312948503 cites W3009407436 @default.
• W4312948503 cites W4214717370 @default.
• W4312948503 cites W60686164 @default.
• W4312948503 doi "https://doi.org/10.1109/tetci.2022.3221483" @default.
• W4312948503 hasPublicationYear "2023" @default.
• W4312948503 type Work @default.
• W4312948503 citedByCount "0" @default.
• W4312948503 crossrefType "journal-article" @default.
• W4312948503 hasAuthorship W4312948503A5005474942 @default.
• W4312948503 hasAuthorship W4312948503A5043861652 @default.
• W4312948503 hasAuthorship W4312948503A5057345644 @default.
• W4312948503 hasAuthorship W4312948503A5060123829 @default.
• W4312948503 hasAuthorship W4312948503A5075938156 @default.
• W4312948503 hasConcept C110121322 @default.
• W4312948503 hasConcept C11413529 @default.
• W4312948503 hasConcept C122507166 @default.
• W4312948503 hasConcept C134306372 @default.
• W4312948503 hasConcept C154945302 @default.
• W4312948503 hasConcept C33923547 @default.
• W4312948503 hasConcept C41008148 @default.
• W4312948503 hasConcept C45357846 @default.
• W4312948503 hasConcept C94375191 @default.
• W4312948503 hasConcept C97541855 @default.
• W4312948503 hasConceptScore W4312948503C110121322 @default.
• W4312948503 hasConceptScore W4312948503C11413529 @default.
• W4312948503 hasConceptScore W4312948503C122507166 @default.
• W4312948503 hasConceptScore W4312948503C134306372 @default.
• W4312948503 hasConceptScore W4312948503C154945302 @default.
• W4312948503 hasConceptScore W4312948503C33923547 @default.
• W4312948503 hasConceptScore W4312948503C41008148 @default.
• W4312948503 hasConceptScore W4312948503C45357846 @default.
• W4312948503 hasConceptScore W4312948503C94375191 @default.
• W4312948503 hasConceptScore W4312948503C97541855 @default.
• W4312948503 hasFunder F4320321001 @default.
• W4312948503 hasIssue "5" @default.
• W4312948503 hasLocation W43129485031 @default.
• W4312948503 hasOpenAccess W4312948503 @default.
• W4312948503 hasPrimaryLocation W43129485031 @default.
• W4312948503 hasRelatedWork W2102043807 @default.
• W4312948503 hasRelatedWork W260766989 @default.
• W4312948503 hasRelatedWork W2959276766 @default.
• W4312948503 hasRelatedWork W3074294383 @default.
• W4312948503 hasRelatedWork W3111983280 @default.
• W4312948503 hasRelatedWork W3139193008 @default.
• W4312948503 hasRelatedWork W3164468573 @default.
• W4312948503 hasRelatedWork W4206669594 @default.
• W4312948503 hasRelatedWork W4226128675 @default.
• W4312948503 hasRelatedWork W4295941380 @default.
• W4312948503 hasVolume "7" @default.
• W4312948503 isParatext "false" @default.
• W4312948503 isRetracted "false" @default.
• W4312948503 workType "article" @default.