Skip to main content
SpringerLink
Log in

Why DGAs work well on GA-hard functions?

  • Regular Papers
  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

What makes a problem easy or hard for a genetic algorithm (GA)? Much previous work has studied this question by applying Walsh analysis.4) In this paper, we demonstrate a function that is GA-hard by analyzing the Walsh coefficients of this function’s Walsh decomposition. Then, we construct five functions with differing degrees of difficulty for genetic algorithms. Some are GA-easy and some are GA-hard. In a previous paper,29) wh have proposed a novel selection method,disruptive selection. This method devotes more trials to both better solutions and worse solutions than it does to moderate solutions, whereas the conventional method allocates its attention according to the performance of each solution. Experimental results show that DGAs (GAs using disruptive selection) perform very well on both GA-easy and GA-hard functions. Finally, we discuss why DGAs outperform conventional GAs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Ackley, D. H.,A Connectionist Machine for Genetic Hillclimbing, Kluwer Academic Publishers, Boston, MA, 1987.

    Google Scholar 

  2. Baker, J. E., “Adaptive Selection Methods for Genetic Algorithms,” inProceedings of the First International Conference on Genetic Algorithms and Their Applications (J. J. Grefenstette, ed.), Hillsdale, NJ, Lawrence Erlbaum Associates, pp. 101–111, July 1985.

    Google Scholar 

  3. Baker, J. E., “Reducing Bias and Inefficiency in the Selection Algorithm,” inProceedings of the Second International Conference on Genetic Algorithms and Their Applications (J. J. Grefenstette, ed.), Hillsdale, NJ, Lawrence-Erlbaum Associates, pp. 14–21, July 1987.

    Google Scholar 

  4. Bethke, A. D., “Genetic Algorithms as Function Optimizers,”Ph.D. thesis, University of Michigan, 1980.

  5. Bhanu, B., Lee, S., and Ming, J., “Self-Optimizing Image Segmentation System Using a Genetic Algorithm,” inProceedings of the Fourth International Conference on Genetic Algorithms and Their Applications (R. K. Belew and L. B. Booker, ed.), San Mateo, CA, Morgan Kaufmann, pp. 362–369, July 1991.

    Google Scholar 

  6. Caruana, R. A. and Schaffer, J. D., “Representation and Hidden Bias: Gray vs. Binary Coding for Genetic Algorithms,” inProceedings of the Fifth International Workshop on Machine Learning (M. B. Morgan, ed.), San Mateo, CA, Morgan Kaufmann, pp. 153–161, June 1988.

    Google Scholar 

  7. Cleveland, G. A. and Smith, S. F., “Using Genetic Algorithms to Schedule Flow Shop Releases,” inProceedings of the Third International Conference on Genetic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 160–169, June 1989.

    Google Scholar 

  8. Dorigo, M. and Schnepf, U., “Genetic-Based Machine Learning and Behavior-Based Robotics: A New Synthesis,”IEEE Transactions on System, Man, and Cybernetics, SMC-23, 1, pp. 141–154, 1993.

    Article  Google Scholar 

  9. Eshelman, L. J., Caruana, R. A., and Schaffer, J. D., “Biases in the Crossover Landscape,” inProceedings of the Third International Conference on Genetic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 10–19, June 1989.

    Google Scholar 

  10. Forrest, S. and Mitchell, M., “The Performance of Genetic Algorithms on Walsh Polynomials: Some Anomalous Results and Their Explanation,” inProceedings of the Fourth International Conference on Genetic Algorithms and Their Applications (R. K. Belew and L. B. Booker, ed.), San Mateo, CA, Morgan Kaufmann, pp. 182–189, July 1991.

    Google Scholar 

  11. Forrest, S. and Mitchell, M.,What Makes a Problem Hard for a Genetic Algorithm? Some Anomalous Results and Their Explanation, Vol. 13, pp. 285–319, 1993.

    Google Scholar 

  12. Goldberg, D. E., “Genetic Algorithms and Walsh Functions: Part 1, A Gentle Introduction,”Complex Systems, 3, pp. 129–152, 1989.

    MATH  MathSciNet  Google Scholar 

  13. Goldberg, D. E., “Genetic Algorithms and Walsh Functions: Part 2, Deception and Its Analysis,”Complex Systems, 3, pp. 153–171, 1989.

    MATH  MathSciNet  Google Scholar 

  14. Goldberg, D. E.,Genetic Algorithms in Search, Optimiztion and Machine Learning, Addison-Wesley, Reading, MA, 1989.

    Google Scholar 

  15. Goldberg, D. E., “Sizing Populations for Serial and Parallel Genetic Algorithms,” inProceedings of the Third International Conference on Genetic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 70–79, June 1989.

    Google Scholar 

  16. Goldberg, D. E. and Lingle, Jr. R., “Alleles, Loci, and the Traveling Salesman Problem,” inProceedings of the First International Conference on Genetic Algorithms and Their Applications (J. J. Grefenstette, ed.), Hillsdale, NJ, Lawrence Erlbaum Associates, pp. 154–159, July 1985.

    Google Scholar 

  17. Goldberg, D. E. and Segrest, P., “Finite Markov Chain Analysis of Genetic Algorithms,” inProceedings of the Second International Conference on Genetic Algorithms and Their Applications (J. J. Grefenstette, ed.), Hillsdale, NJ, Lawrence Erlbaum Associates, pp. 1–8, July 1987.

    Google Scholar 

  18. Goldberg, D. E. and Deb Kalyanmoy, “A Comparative Analysis of Selection Schemes Used in Genetic Algorithms,” inFoundations of Genetic Algorithms (G. J. E. Rawlins, ed.), San Mateo, CA, Morgan Kaufmann, pp. 69–93, 1991.

    Google Scholar 

  19. Grefenstette, J. J., “Optimization of Control Parameters for Genetic Algorithms,”IEEE Transactions on System, man, and Cybernetics, SMC-16, 1, pp. 122–128, 1986.

    Article  Google Scholar 

  20. Grefenstette, J. J., “Credit Assignment in Rule Discovery Systems Based on Genetic Algorithms,”Machine Learning, 3, 2/3, pp. 225–245, 1988.

    Article  Google Scholar 

  21. Grefenstette, J. J. and Baker, J. E., “How Genetic Algorithms Work: A Critical Look at Implicit Parallelism,” inProceedings of the Third International Conference on Genetic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 20–27, June 1989.

    Google Scholar 

  22. Gerfenstette, J. J., Gopal, R., Rosmaita, B. J., and Gucht, D. V., “Genetic Algorithms for the Traveling Salesman Problem,” inProceedings of the First International Conference on Genetic Algorithms and Their Applications (J. J. Grefenstette, ed.), Hillsdale, NJ, Lawrence Erlbaum Associates, pp. 160–168, July, 1985.

    Google Scholar 

  23. Harp, S. A., Samad, T., and Guha, A., “Towards the Genetic Synthesis of Neural Networks,” inProceedings of the Third International Conference on Genetic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 360–369, June 1989.

    Google Scholar 

  24. Holland, J. H.,Adaptation in Natural and Artificial Systems, Ann Arbor, MI, the University of Michigan Press, 1975.

    Google Scholar 

  25. De Jong, K. A., “An Analysis of the Behavior of a Class of Genetic Adaptive Systems,”Ph.D. thesis, University of Michigan, 1975.

  26. Karr, C. L., “Design of an Adaptive Fuzzy Logic Controller Using a Genetic Algorithm,” inProceedings of the Fourth International Conference on Genetic Algorithms and Their Applications (R. K. Belew and L. B. Booker, eds.), San Mateo, CA, Morgan Kaufmann, pp. 450–457, July 1991.

    Google Scholar 

  27. Kristinsson, K. and Dumont, G. A., “System Identification and Control Using Genetic Algorithms,”IEEE Transactions on System, Man, and Cybernetics, SMC-22, 5, pp. 1033–1046, 1992.

    Article  MATH  Google Scholar 

  28. Kuo, T. and Hwang, S. Y., “A Genetic Algorithm with Disruptive Selection,”IEEE Transactions on System, Man, and Cybernetics, SMC-26, 2, pp. 299–307, 1996.

    Article  Google Scholar 

  29. Kuo, T. and Hwang, S. Y., “A Genetic Algorithm with Disruptive Selection,” inProceedings of the Fifth International Conference on Genetic Algorithms (S. Forrest, ed.), San Mateo, CA, Morgan Kaufmann, pp. 65–69, July 1993.

    Google Scholar 

  30. Mahfoud, S. W., “Niching Methods for Genetic Algorithms,”Ph.D. thesis, University of Illinois at Urbana-Champaign, 1995.

  31. Miller, G. F., Todd, P. M., and Hegde, S. U., “Designing Neural Networks Using Genetic Algorithms,” inProceedings of the Third International Conference on Genetic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 379–384, June 1989.

    Google Scholar 

  32. Mitchell, M., Forrest, S., and Holland, J. H., “The Royal Road for Genetic Algorithms: Fitness Landscapes and Ga Performance”, inProceedings of the First European Conference on Artificial Life, 1992.

  33. Schaffer, J. D., “Some experiments in Machine Learning Using Vector Evaluated Genetic Algorithms,”Ph.D. thesis, Vanderbilt University, 1980.

  34. Schaffer, J. D. and Morishima, A., “An Adaptive Crossover Distribution Mechanism for Genetic Algorithms,” inProceedings of the Second International Conference on Genetic Algorithms and Their Applications (J. J. Grefenstette, ed.), Hillsdale, NJ, Lawrence Erlbaum Associates, pp. 36–40, July 1987.

    Google Scholar 

  35. Syswerda, G., “Uniform Crossover in Genetic Algorithms,” inProceedings of the Third International Conference on Gentic Algorithms and Their Applications (J. D. Schaffer, ed.), San Mateo, CA, Morgan Kaufmann, pp. 2–9, June 1989.

    Google Scholar 

  36. Syswerda, G. and Palmucci, J., “The Application of Genetic Algorithm to Resource Scheduling,” inProceedings of the Fourth International Conference on Genetic Algorithms and Their Applications (R. K. Belew and L. B. Booker, eds.), San Mateo, CA, Morgan Kaufmann, pp. 502–508, July 1991.

    Google Scholar 

  37. Whitley, D. and Kauth, J., “Genitor: A different Genetic Algorithm.,” inProc. of Rocky Mountain Conference on Artificial Intelligence, pp. 118–130, 1988.

  38. Wilson, S. W., “Ga-Easy Does Not Imply Steepest-Ascent Optimizable,” inProceedings of the Fourth International Conference on Genetic Algorithms and Their Applications (R. K. Belew and L. B. Booker, eds.) San Mateo, CA, Morgan Kaufmann, pp. 85–89. July 1991.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Information Engineering, National Chiao Tung University, Hsinchu, Taiwan, Republic of China

    Ting Kuo & Shu -Yuen Hwang

Authors
  1. Ting Kuo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shu -Yuen Hwang
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Ting Kuo Ph.D.: He received the B. S. degree in Industrial Engineering from National Tsing Hua University, in 1979. From 1979 to 1981, he served in the Chinese Army as a logistics officer. From Dec. 1981 to Aug. 1982, he worked at Shih-Lin Dyeing & Weaving Co., Ltd. as an Industrial Engineer. From May 1983 to Aug. 1991, he worked at the Technical Research Division of the Institute for Information Industry, Taipei, Taiwan. He received his M.S. and Ph.D. degrees both in the Department of Computer Science and Information Engineering at National Chiao Tung University in 1990 and 1995. His current research interests include Genetic Algorithms, Artificial Intelligence, and Optimization.

Shu-Yuen Hwang, Ph.D.: He received the B. S. and M. S. degrees in Electrical Engineering from National Taiwan University, in 1981 and 1983, respectively. From 1983 to 1985, he served in the Chinese Army as an officer. He received the Ph.D. degree in the Department of Computer Science at University of Washington in 1989. Since 1989, he has been with the Department of Computer Science and Information Engineering, National Chiao Tung University. From 1993 to 1995, he served as the director of the graduate institute. He is now a professor and the deputy director of the Computer Systems Research Center. His current research interests include Artificial Intelligence and Mobile Computing.

About this article

Cite this article

Kuo, T., Hwang, S.Y. Why DGAs work well on GA-hard functions?. NGCO 14, 459–479 (1996). https://doi.org/10.1007/BF03037213

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03037213

Keywords

Search

Navigation