ABSTRACT
Hierarchical problems represent an important class of nearly decomposable problems and come from hierarchical complex systems. Complex systems are important since they appear in a variety of different areas. The dependency structure matrix genetic algorithm II, performing exploration and exploitation properly, requires fewer number of function evaluations on several problems than some well-known evolutionary algorithms such as the linkage tree genetic algorithm and the hierarchical bayesian optimization algorithm. However, DSMGA-II does not preserve enough promising subsolutions to the upper levels in hierarchical problems due to the back mixing operator of DSMGA-II, so it fails to solve the hierarchical trap problem. This paper proposes a diversity preservation scheme for DSMGA-II to conquer the hierarchical difficulty by calculating the entropies of subsolutions and determining whether to perform the back mixing. The empirical results show that our algorithm works well on hierarchical problems and does not compromise the performance on other problems.
- Peter A.N. Bosman and Dirk Thierens. 2012. Linkage neighbors, optimal mixing and forced improvements in genetic algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2012). 585--592. Google ScholarDigital Library
- Wei-Ming Chen, Chu-Yu Hsu, Tian-Li Yu, and Wei-Che Chien. 2013. Effects of discrete hill climbing on model building forestimation of distribution algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2013). 367--374. Google ScholarDigital Library
- Kalyanmoy Deb and David E. Goldberg. 1994. Sufficient conditions for deceptive and easy binary functions. Annals of Mathematics and Artificial Intelligence 10 (1994), 385--408.Google ScholarCross Ref
- David E. Goldberg. 2002. The Design of Innovation: Lessons from and for Competent Genetic Algorithms. Kluwer Academic Publishers, Boston, MA. Google ScholarDigital Library
- David E. Goldberg, Kalyanmoy Deb, and Jeffrey Horn. 1992. Massive Multimodality, Deception, and Genetic Algorithms. (1992).Google Scholar
- Brian W. Goldman and William F. Punch. 2014. Parameterless population pyramid. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014). 785--792. Google ScholarDigital Library
- Georges Harik. 1995. Finding multimodal solutions using restricted tournament selection. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 1995). 24--31. Google ScholarDigital Library
- John H. Holland. 1975. Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor, MI.Google Scholar
- Shih-Huan Hsu and Tian-Li Yu. 2015. Optimization by pairwise linkage detection, incremental linkage set, and restricted/back mixing: DSMGA-II. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2015). 519--526. Google ScholarDigital Library
- Soloman Kullback and Richard A. Leibler. 1951. On information and sufficiency. The Annals of Mathematical Statistics 22, 1 (1951), 79--86.Google ScholarCross Ref
- Pedro Larranaga and Jose A. Lozano. 2002. Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation. Kluwer Academic Publishers, Boston, MA. Google ScholarDigital Library
- Ngoc Hoang Luong, Han La Poutré, and Peter A.N. Bosman. 2014. Multi-objective gene-pool optimal mixing evolutionary algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014). 357--364. Google ScholarDigital Library
- Martin Pelikan. 2005. Hierarchical Bayesian optimization algorithm. Springer, Berlin Heidelberg.Google Scholar
- Martin Pelikan and David E. Goldberg. 2000. Hierarchical Problem Solving and the Bayesian Optimization Algorithm. In Genetic and Evolutionary Computation Conference. 267--274. Google ScholarDigital Library
- Martin Pelikan and David E. Goldberg. 2000. Hierarchical problem solving and the Bayesian optimization algorithm. In Proceedings of the Genetic and Evolutionary Computation Conference. 267--274. Google ScholarDigital Library
- Martin Pelikan and David E. Goldberg. 2001. Escaping hierarchical traps with competent genetic algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2001). 511--518. Google ScholarDigital Library
- Martin Pelikan, David E. Goldberg, and Shigeyoshi Tsutsui. 2003. Hierarchical Bayesian optimization algorithm: toward a new generation of evolutionary algorithms. In SICE 2003 Annual Conference. 2738--2743.Google Scholar
- Martin Pelikan, Kumara Sastry, David E. Goldberg, Martin V. Butz, and Mark Hauschild. 2009. Performance of evolutionary algorithms on nk landscapes with nearest neighbor interactions and tunable overlap. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2009). 851--858. Google ScholarDigital Library
- Krzysztof L. Sadowski, Peter A.N. Bosman, and Dirk Thierens. 2013. On the usefulness of linkage processing for solving max-sat. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2013). 853--860. Google ScholarDigital Library
- Claude E. Shannon. 1948. A mathematical theory of communication. The Bell System Technical Journal 27 (1948), 379--423.Google ScholarCross Ref
- Dirk Thierens. 2010. The linkage tree genetic algorithm. In International Conference on Parallel Problem Solving from Nature: Part I (PPSN 2010). 264--273. Google ScholarDigital Library
- Dirk Thierens and Peter A.N. Bosman. 2011. Optimal mixing evolutionary algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2011). 617--624. Google ScholarDigital Library
- Dirk Thierens and Peter A.N. Bosman. 2013. Hierarchical problem solving with the linkage tree genetic algorithm. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2013). 877--884. Google ScholarDigital Library
- Matej Črepinšek, Shih-Hsi Liu, and Marjan Mernik. 2013. Exploration and exploitation in evolutionary algorithms: A survey Comput. Surveys 3 (July 2013), 35:1--35:33. Google ScholarDigital Library
- Richard A. Watson, Gregory S. Hornby, and Jordan B. Pollack. 1998. Modeling building-block interdependency. Parallel Problem Solving from Nature (1998), 97--106. Google ScholarDigital Library
- Richard A. Watson and Jordan B. Pollack. 1999. Hierarchically consistent test problems for genetic algorithms : Summary and additional results. Late breaking papers at the Genetic and Evolutionary Computation Conference (1999), 292--297.Google Scholar
- Tian-Li Yu and David E. Goldberg. 2006. Conquering hierarchical difficulty by explicit chunking: substructural chromosome compression. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2006). 1385--1392. Google ScholarDigital Library
- Tian-Li Yu, Kumara Sastry, and David E. Goldberg. 2005. Linkage learning, overlapping building blocks, and systematic strategy for scalable recombination. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2005). 1217--1224. Google ScholarDigital Library
- Tian-Li Yu, Kumara Sastry, David E. Goldberg, and Martin Pelikan. 2007. Population sizing for entropy-based model building in discrete estimation of distribution algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2007). 601--608. Google ScholarDigital Library
Index Terms
- A diversity preservation scheme for DSMGA-II to conquer the hierarchical difficulty
Recommendations
Comparative mixing for DSMGA-II
GECCO '20: Proceedings of the 2020 Genetic and Evolutionary Computation ConferenceDependency Structure Matrix Genetic Algorithm-II (DSMGA-II) is a recently proposed optimization method that builds the linkage model on the base of the Dependency Structure Matrix (DSM). This model is used during the Optimal Mixing (OM) operators, such ...
Parameter-less, population-sizing DSMGA-II
GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference CompanionLimiting the number of required settings is an important part of any evolutionary method development. The final objective of this process is a method version that is parameter-less. Based on the research results presented that far, the leading methods ...
A linkage-learning niching in estimation of distribution algorithm
GECCO '12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computationThis work proposes a linkage-learning niching method that improves the capability of estimation of distribution algorithms (EDAs) on reducing spurious linkages which increase problems difficulty. Concatenated parity function (CPF), a class of allelic ...
Comments