previous  home  search  LaTeX  -  PostScript  -  PDF  -  Html/Gif   contact    up    next  

Tournament versus Fitness Uniform Selection


Authors: Shane Legg and Marcus Hutter and Akshat Kumar (2004)
Comments: 10 pages
Subj-class: Learning; Artificial Intelligence
Reference: Proc. 2004 Congress on Evolutionary Computation (CEC 2004) pages 2144-2151
Report-no: IDSIA-04-04 and cs.LG/0403038
Paper: LaTeX  -  PostScript  -  PDF  -  Html/Gif 
Slides: PowerPoint
C++ Code:FussDD.cpp - FussDD.h - FussTSP.cpp - FussTSP.h
Review/Survey: in the Technology Reseach News Magazine (cached)

Keywords: Selection schemes, fitness evaluation, optimization, fitness landscapes, basic working principles of evolutionary computations, (self)adaptation, evolutionary algorithm, deceptive & multimodal optimization problems.

Abstract: In evolutionary algorithms a critical parameter that must be tuned is that of selection pressure. If it is set too low then the rate of convergence towards the optimum is likely to be slow. Alternatively if the selection pressure is set too high the system is likely to become stuck in a local optimum due to a loss of diversity in the population. The recent Fitness Uniform Selection Scheme (FUSS) is a conceptually simple but somewhat radical approach to addressing this problem - rather than biasing the selection towards higher fitness, FUSS biases selection towards sparsely populated fitness levels. In this paper we compare the relative performance of FUSS with the well known tournament selection scheme on a range of problems.

 previous  home  search  LaTeX  -  PostScript  -  PDF  -  Html/Gif   contact    up    next  

BibTeX Entry

@InProceedings{Hutter:04fussexp,
  author =       "S. Legg and M. Hutter and A. Kumar",
  title =        "Tournament versus Fitness Uniform Selection",
  booktitle =    "Proc. 2004 Congress on Evolutionary Computation (CEC-2004)",
  address =      "Portland, OR",
  publisher =    "IEEE",
  ISBN =         "0-7803-8515-2",
  year =         "2004",
  pages =        "2144--2151",
  keywords =     "Selection schemes, fitness evaluation, optimization,
                  fitness landscapes, basic working principles of evolutionary computations,
                  (self)adaptation, evolutionary algorithm,
                  deceptive \& multimodal optimization problems.",
  http =         "http://www.hutter1.net/ai/fussexp.htm",
  url =          "http://arxiv.org/abs/cs.LG/0403038",
  ftp =          "ftp://ftp.idsia.ch/pub/techrep/IDSIA-04-04.pdf",
  abstract =     "In evolutionary algorithms a critical parameter that must be tuned is
                  that of selection pressure.  If it is set too low then the rate of
                  convergence towards the optimum is likely to be slow.  Alternatively
                  if the selection pressure is set too high the system is likely to
                  become stuck in a local optimum due to a loss of diversity in the
                  population. The recent Fitness Uniform Selection Scheme (FUSS) is a
                  conceptually simple but somewhat radical approach to addressing this
                  problem --- rather than biasing the selection towards higher fitness,
                  FUSS biases selection towards sparsely populated fitness levels. In
                  this paper we compare the relative performance of FUSS with the well
                  known tournament selection scheme on a range of problems.",
}
 previous  home  search  LaTeX  -  PostScript  -  PDF  -  Html/Gif   contact    up    next