ABSTRACT
The choice of which of the available strategies should be used within the Differential Evolution algorithm for a given problem is not trivial, besides being problem-dependent and very sensitive with relation to the algorithm performance. This decision can be made in an autonomous way, by the use of the Adaptive Strategy Selection paradigm, that continuously selects which strategy should be used for the next offspring generation, based on the performance achieved by each of the available ones on the current optimization process, i.e., while solving the problem. In this paper, we use the BBOB-2010 noiseless benchmarking suite to better empirically validate a comparison-based technique recently proposed to do so, the Fitness-based Area-Under-Curve Bandit [4], referred to as F-AUC-Bandit. It is compared with another recently proposed approach that uses Probability Matching technique based on the relative fitness improvements, referred to as PM-AdapSS-DE [7].
- P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multi-armed bandit problem. Machine Learning, 47(2-3):235--256, 2002. Google ScholarDigital Library
- M. Birattari, T. Stützle, L. Paquete, and K. Varrentrapp. A racing algorithm for configuring metaheuristics. In W. B. Langdon et al., editor, Proc. Genetic Evol. Comput. Conf., pages 11--18. Morgan Kaufmann, 2002.Google Scholar
- A. P. Bradley. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 30:1145--1159, 1997. Google ScholarDigital Library
- A. Fialho, M. Schoenauer, and M. Sebag. Toward comparison-based adaptive operator selection. In J. Branke et al., editor, Proc. Genetic Evol. Comput. Conf. ACM Press, 2010. Google ScholarDigital Library
- S. Finck, N. Hansen, R. Ros, and A. Auger. Real-parameter black-box optimization benchmarking 2009: Presentation of the noiseless functions. Technical Report 2009/20, Research Center PPE, 2009. Updated February 2010.Google Scholar
- D. E. Goldberg. Probability matching, the magnitude of reinforcement, and classifier system bidding. Mach. Learn., 5(4):407--425, 1990. Google ScholarDigital Library
- W. Gong, A. Fialho, and Z. Cai. Adaptive strategy selection in differential evolution. In J. Branke et al., editor, Proc. Genetic Evol. Comput. Conf. ACM Press, 2010. Google ScholarDigital Library
- N. Hansen, A. Auger, S. Finck, and R. Ros. Real-parameter black-box optimization benchmarking 2010: Experimental setup. Technical Report RR-7215, INRIA, 2010.Google Scholar
- N. Hansen, S. Finck, R. Ros, and A. Auger. Real-parameter black-box optimization benchmarking 2009: Noiseless functions definitions. Technical Report RR-6829, INRIA, 2009. Updated February 2010.Google Scholar
- A. W. Iorio and X. Li. Improving the performance and scalability of differential evolution. In Proc. Conf. Simulated Evol. and Learning, pages 131--140. Springer-Verlag, 2008. Google ScholarDigital Library
- J. Maturana, A. Fialho, F. Saubion, M. Schoenauer, and M. Sebag. Extreme compass and dynamic multi-armed bandits for adaptive operator selection. In Proc. IEEE Congress on Evol. Comp., pages 365--372. IEEE Press, 2009. Google ScholarDigital Library
- J. Maturana, F. Lardeux, and F. Saubion. Autonomous operator management for evolutionary algorithms. J. of Heuristics, 2010. Google ScholarDigital Library
- K. Price. Differential evolution vs. the functions of the second ICEO. In Proc. IEEE Congress on Evol. Comp., pages 153--157, 1997.Google Scholar
- K. Price, R. Storn, and J. Lampinen. Differential Evolution: A Practical Approach to Global Optimization. Springer-Verlag, Berlin, 2005. Google ScholarDigital Library
- A. K. Qin, V. L. Huang, and P. N. Suganthan. Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans. on Evol. Comput., 13(2):398--417, Apr 2009. Google ScholarDigital Library
- R. Storn and K. Price. Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces. J. of Global Optim., 11(4):341--359, Dec 1997. Google ScholarDigital Library
- D. Thierens. An adaptive pursuit strategy for allocating operator probabilities. In Proc. Genetic Evol. Comput. Conf., pages 1539--1546, 2005. Google ScholarDigital Library
Index Terms
- Fitness-AUC bandit adaptive strategy selection vs. the probability matching one within differential evolution: an empirical comparison on the bbob-2010 noiseless testbed
Recommendations
Probability matching-based adaptive strategy selection vs. uniform strategy selection within differential evolution: an empirical comparison on the bbob-2010 noiseless testbed
GECCO '10: Proceedings of the 12th annual conference companion on Genetic and evolutionary computationDifferent strategies can be used for the generation of new candidate solutions on the Differential Evolution algorithm. However, the definition of which of them should be applied to the problem at hand is not trivial, besides being a sensitive choice ...
JADE, an adaptive differential evolution algorithm, benchmarked on the BBOB noiseless testbed
GECCO '12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computationJADE, an adaptive version of the differential evolution (DE) algorithm, is benchmarked on the testbed of 24 noiseless functions chosen for the Black-Box Optimization Benchmarking workshop. The results of full-featured JADE are then compared with the ...
Asynchronous differential evolution with adaptive correlation matrix
GECCO '13: Proceedings of the 15th annual conference on Genetic and evolutionary computationDifferential evolution (DE) is an efficient algorithm to solve global optimization problems. It has a simple internal structure and uses a few control parameters. In this paper we incorporate crossover based on adaptive correlation matrix into ...
Comments