Advertisement

Instance-Based Parameter Tuning via Search Trajectory Similarity Clustering

  • Lindawati
  • Hoong Chuin Lau
  • David Lo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6683)

Abstract

This paper is concerned with automated tuning of parameters in local-search based meta-heuristics. Several generic approaches have been introduced in the literature that returns a ”one-size-fits-all” parameter configuration for all instances. This is unsatisfactory since different instances may require the algorithm to use very different parameter configurations in order to find good solutions. There have been approaches that perform instance-based automated tuning, but they are usually problem-specific. In this paper, we propose CluPaTra, a generic (problem-independent) approach to perform parameter tuning, based on CLUstering instances with similar PAtterns according to their search TRAjectories. We propose representing a search trajectory as a directed sequence and apply a well-studied sequence alignment technique to cluster instances based on the similarity of their respective search trajectories. We verify our work on the Traveling Salesman Problem (TSP) and Quadratic Assignment Problem (QAP). Experimental results show that CluPaTra offers significant improvement compared to ParamILS (a one-size-fits-all approach). CluPaTra is statistically significantly better compared with clustering using simple problem-specific features; and in comparison with the tuning of QAP instances based on a well-known distance and flow metric classification, we show that they are statistically comparable.

Keywords

instance-based automated tuning parameter search trajectory sequence alignment instance clustering 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Adenso-Diaz, B., Laguna, M.: Fine-Tuning of Algorithms Using Fractional Experimental Design and Local Search. Operations Research 54(1), 99–114 (2006)CrossRefzbMATHGoogle Scholar
  2. 2.
    Battiti, R., Brunato, M., Campigotto, P.: Learning While Optimizing an Unknown Fitness Surface. In: Maniezzo, V., Battiti, R., Watson, J.-P. (eds.) LION 2007 II. LNCS, vol. 5313, pp. 25–40. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  3. 3.
    Birattari, M., Stuzle, T., Paquete, L., Varrentrapp, K.: A Racing Algorithm for Configuring Metaheuristics. In: Genetic and Evolutionary Computation Conference, pp. 11–18. Morgan Kaufmann, San Francisco (2002)Google Scholar
  4. 4.
    Coy, S.P., Golden, B.L., Runger, G.C., Wasil, E.A.: Using Experimental Design to Find Effective Parameter Setting for Heuristics. Journal of Heuristic 7(1), 77–97 (2001)CrossRefzbMATHGoogle Scholar
  5. 5.
    Edgar, R.C.: MUSCLE: multiple sequence alignment with high accuracy and high throughput. Nucleic Acids Research 35(5), 1792–1797 (2004)CrossRefGoogle Scholar
  6. 6.
    Gagliolo, M., Schmidhuber, J.: Dynamic Algorithm Portfolio. In: Amato, C., Bernstein, D., Zilberstein, S. (eds.) Ninth International Symposium on Artificial Intelligence and Mathematics (2006)Google Scholar
  7. 7.
    Halim, S., Yap, R., Lau, H.C.: Viz: A Visual Analysis Suite for Explaining Local Search Behavior. In: 19th Annual ACM Symposium on User Interface Software and Technology, pp. 57–66. ACM, New York (2006)Google Scholar
  8. 8.
    Halim, S., Yap, R., Lau, H.C.: An Integrated White+Black Box Approach for Designing and Tuning Stochastic Local Search. In: Bessière, C. (ed.) CP 2007. LNCS, vol. 4741, pp. 332–347. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Han, J., Kamber, M.: Data Mining: Concept and Techniques, 2nd edn. Morgan Kaufman, San Francisco (2006)zbMATHGoogle Scholar
  10. 10.
    Hoos, H.H., Stutzle, T.: Stochastic Local Search: Foundation and Application, 1st edn. Morgan Kaufman, San Francisco (2004)zbMATHGoogle Scholar
  11. 11.
    Hutter, F., Hamadi, Y.: Parameter Adjustment Based on Performance Prediction: Towards an Instance-Aware Problem Solver. Technical Report, Microsoft Research (2005)Google Scholar
  12. 12.
    Hutter, F., Hoos, H.H., Stutzle, T.: Automatic Algorithm Configuration based on Local Search. In: 22nd National Conference on Artifical Intelligence, pp. 1152–1157. AAAI Press, Menlo Park (2007)Google Scholar
  13. 13.
    Hutter, F., Hoos, H.H., Leyton-Brown, K., Stutzle, T.: ParamILS: An Automatic Algorithm Configuration Framework. Journal of Artificial Intelligence Research 36, 267–306 (2009)zbMATHGoogle Scholar
  14. 14.
    Lau, H.C., Xiao, F.: Enhancing the Speed and Accuracy of Automated Parameter Tuning in Heuristic Design. In: 8th Metaheuristics International Conference (2009)Google Scholar
  15. 15.
    Lourenco, H.R., Martin, O.C., Stutzle, T.: Iterated Local Search. In: Glover, F., Kochenberger, G.A. (eds.) Handbook of Metaheuristics. International Series in Operations Research & Management Science, vol. 57, pp. 320–353. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  16. 16.
    Merz, P., Freisleben, B.: Fitness Landscape Analysis and Memetic Algorithms for the Quadratic Assignment Problem. IEEE Transactions on Evolutionary Computation 4, 337–351 (2000)CrossRefGoogle Scholar
  17. 17.
    Montgomery, D.C., Runger, G.C.: Applied Statistics and Probability for Engineers, 2nd edn. John Wiley & Son, Chichester (1999)zbMATHGoogle Scholar
  18. 18.
    Ng, K.M., Gunawan, A., Poh, K.L.: A hybrid algorithm for the quadratic assignment problem. In: International Conf. on Scientific Computing (2008)Google Scholar
  19. 19.
    Patterson, D.J., Lautz, H.: Auto-WalkSAT: A Self-Tuning Implementation of WalkSAT. Electronic Notes in Discrete Mathematics 9, 360–368 (2001)CrossRefzbMATHGoogle Scholar
  20. 20.
    Reeves, C.R.: Landscapes, operators and heuristic search. Annals of Operations Research 86(1), 473–490 (1999)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Salvador, S., Chan, P.: Determining the Number of Clusters/Segments in Hierarchical Clustering/Segmentation Algorithms. In: 16th IEEE International Conference on Tools with Artificial Intelligence, pp. 576–584 (2004)Google Scholar
  22. 22.
    Srivastava, B., Mediratta, A.: Domain-dependent parameter selection of search-based algorithms compatible with user performance criteria. In: 20th National Conference on Artificial Intelligence, pp. 1386–1391. AAAI Press, Pennsylvania (2005)Google Scholar
  23. 23.
    Taillard, E.D.: Comparison of Iterative Searches for The Quadratic Assignment Problem. Location Science 3(2), 87–105 (1995)CrossRefzbMATHGoogle Scholar
  24. 24.
    Xu, L., Hutter, F., Hoos, H.H., Leyton-Brown, K.: SATzilla: Portfolio-based Algorithm Selection for SAT. Journal of Artificial Intelligence Research 32, 565–606 (2008)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Lindawati
    • 1
  • Hoong Chuin Lau
    • 1
  • David Lo
    • 1
  1. 1.School of Information SystemsSingapore Management UniversitySingapore

Personalised recommendations