ABSTRACT
Many important problem classes lead to large variations in fitness evaluation times, such as is often the case in Genetic Programming where the time complexity of executing one individual may differ greatly from that of another. Asynchronous Parallel Evolutionary Algorithms (APEAs) omit the generational synchronization step of traditional EAs which work in well-defined cycles. This paper provides an empirical analysis of the scalability improvements obtained by applying APEAs to such problem classes, aside from the speed-up caused merely by the removal of the synchronization step. APEAs exhibit bias towards individuals with shorter fitness evaluation times, because they propagate faster. This paper demonstrates how this bias can be leveraged in order to provide a unique type of "elitist" parsimony pressure which rewards more efficient solutions with equal solution quality.
- S. Bleuler, M. Brack, L. Thiele, and E. Zitzler. Multiobjective Genetic Programming: Reducing Bloat Using SPEA2. In Proceedings of the 2001 Congress on Evolutionary Computation, volume 1, pages 536--543. IEEE, 2001.Google ScholarCross Ref
- A. W. Churchill, P. Husbands, and A. Philippides. Tool Sequence Optimization using Synchronous and Asynchronous Parallel Multi-Objective Evolutionary Algorithms with Heterogeneous Evaluations. In 2013 IEEE Congress on Evolutionary Computation (CEC), pages 2924--2931. IEEE, 2013.Google ScholarCross Ref
- J. Miller. What bloat? Cartesian Genetic Programming on Boolean problems. In 2001 Genetic and Evolutionary Computation Conference Late Breaking Papers, pages 295--302, 2001.Google Scholar
- M. Mitchell, S. Forrest, and J. H. Holland. The Royal Road for Genetic Algorithms: Fitness Landscapes and GA Performance. In Proceedings of the First European Conference on Artificial Life, pages 245--254. Cambridge: The MIT Press, 1992.Google Scholar
- M. Yagoubi and M. Schoenauer. Asynchronous Master/Slave MOEAs and Heterogeneous Evaluation Costs. In Proceedings of the Fourteenth International Conference on Genetic and Evolutionary Computation Conference, pages 1007--1014. ACM, 2012. Google ScholarDigital Library
- M. Yagoubi, L. Thobois, and M. Schoenauer. Asynchronous Evolutionary Multi-Objective Algorithms with Heterogeneous Evaluation Costs. In 2011 IEEE Congress on Evolutionary Computation (CEC), pages 21--28. IEEE, 2011.Google ScholarCross Ref
Index Terms
- Asynchronous Parallel Evolutionary Algorithms: Leveraging Heterogeneous Fitness Evaluation Times for Scalability and Elitist Parsimony Pressure
Recommendations
Asynchronous and implicitly parallel evolutionary computation models
This paper presents the design and the application of asynchronous models of parallel evolutionary algorithms. An overview of the existing parallel evolutionary algorithm (PEA) models and available implementations is given. We present new PEA models in ...
Asynchronous Differential Evolution with Strategy Adaptation for Global Numerical Optimization
HPCCT '18: Proceedings of the 2018 2nd High Performance Computing and Cluster Technologies ConferenceA new variant of Differential Evolution (DE) algorithm called A-SaDE algorithm is proposed. A-SaDE algorithm is based on two DE variants, Self-adaptive DE (SaDE) and Asynchronous DE (ADE) algorithms. SaDE algorithm is one of the well-known DE algorithms ...
Adaptive asynchrony in semi-asynchronous evolutionary algorithm based on performance prediction using search history
GECCO '18: Proceedings of the Genetic and Evolutionary Computation ConferenceThis paper proposes an adaptation technique in an asynchronous evolutionary algorithm (EA) and verifies its effectiveness on multi-objective optimization problems. A parallel EA, which executes EA on a parallel computational environment, can be ...
Comments