Advertisement

Algorithm Configuration: Learning Policies for the Quick Termination of Poor Performers

  • Daniel KarapetyanEmail author
  • Andrew J. Parkes
  • Thomas Stützle
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11353)

Abstract

One way to speed up the algorithm configuration task is to use short runs instead of long runs as much as possible, but without discarding the configurations that eventually do well on the long runs. We consider the problem of selecting the top performing configurations of Conditional Markov Chain Search (CMCS), a general algorithm schema that includes, for example, VNS. We investigate how the structure of performance on short tests links with those on long tests, showing that significant differences arise between test domains. We propose a “performance envelope” method to exploit the links; that learns when runs should be terminated, but that automatically adapts to the domain.

References

  1. 1.
    Hutter, Frank, Hoos, Holger H., Leyton-Brown, Kevin: Sequential model-based optimization for general algorithm configuration. In: Coello, Carlos A.Coello (ed.) LION 2011. LNCS, vol. 6683, pp. 507–523. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-25566-3_40CrossRefGoogle Scholar
  2. 2.
    Karapetyan, D., Goldengorin, B.: Conditional Markov Chain Search for the simple plant location problem improves upper bounds on twelve Korkel-Ghosh instances. In: Goldengorin B. (ed.) Optimization Problems in Graph Theory, pp. 123–147. Springer (2018).  https://doi.org/10.1007/978-3-319-94830-0
  3. 3.
    Karapetyan, D., Punnen, A.P., Parkes, A.J.: Markov chain methods for the bipartite boolean quadratic programming problem. Eur. J. Oper. Res. 260(2), 494–506 (2017).  https://doi.org/10.1016/j.ejor.2017.01.001MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Daniel Karapetyan
    • 1
    Email author
  • Andrew J. Parkes
    • 2
  • Thomas Stützle
    • 3
  1. 1.Institute for Analytics and Data ScienceUniversity of EssexColchesterUK
  2. 2.ASAP Research Group, School of Computer ScienceUniversity of NottinghamNottinghamUK
  3. 3.IRIDIA, CoDE, Universit Libre de Bruxelles (ULB)BrusselsBelgium

Personalised recommendations