| Workshop on Parameter Setting in Genetic and Evolutionary Algorithms (PSGEA 2005) |
||||||||||||||||
|
||||||||||||||||
| [ Scope ] [ Participation ] [ Important Dates ] [ Attendance ] [ Program Schedule ] [ Chairs ] [ Program Committee ] [ Talk Abstracts ] | ||||||||||||||||
 |
||||||||||||||||
|
||||||||||||||||
| Scope | ||||||||||||||||
|
One of the main difficulties that a user faces when applying a
GEA is on deciding on an appropriate set of parameter values.
Before running the algorithm, the user has to specify a number of
parameters, such as population size, selection rate, crossover
probability, and mutation probability. Over the years, there has been
a variety of research studies with the purpose of understanding
parameter interactions, as well as different approaches to
automate parameter setting in GEAs. In this workshop we would like
to have an open discussion on the following topics: - Interactions among GEA parameters, - Behavior of one (or more) specific GEA parameter, - Practical guidelines for parameter configuration and trade-off in GEAs, - Parameter setting in GEAs for real-world problems, - Deterministic and adaptive parameter-less techniques for GEAs, - Self-adaptive parameter-less techniques for GEAs, - Benefits and drawbacks of the different approaches to automate parameter setting in GEAs. The length of the workshop is 4 hours. The workshop will start with an introduction by the organizers. This will be followed by about 5-7 presentations. The workshop will finish with a panel discussion. [ back to top ] |
||||||||||||||||
| Participation | ||||||||||||||||
|
Presentations will be selected according to the submitted papers (with a maximum
length of 12 pages) which will be reviewed by at least two members of the
international program committee. All accepted papers will be included in the
workshop proceedings that will be available at GECCO-2005 check in.
Papers should be submitted in electronic PDF format following the
GECCO paper format.
When submitting your paper please use the following subject:
"PSGEA submission". Extended versions of selected papers presented at the workshop will be published in a book entitled "Parameter Setting in Genetic and Evolutionary Algorithms", which will be part of the new series Studies in Computational Intelligence by Springer. If you have any question please contact the workshop organizers. [ back to top ] |
||||||||||||||||
| Importante Dates | ||||||||||||||||
The following dates are preliminary and are subject to change:
[ back to top ] |
||||||||||||||||
| Attendance | ||||||||||||||||
|
Attendance to the workshop is open to all GECCO attendees.
We particularly welcome researchers who have been working on the topic
of automating parameter settings in GEAs, and practitioners who want
to apply GEAs for problem solving but that are often confused with the
nuts and bolts of parameter settings. We are looking forward to your participation! [ back to top ] |
||||||||||||||||
| Program Schedule | ||||||||||||||||
|
8:30 -- 8:45 Introduction by the Workshop Organizers 8:45 -- 9:30 Invited Talk: Population Sizing for Genetic Programming Based Upon Decision Making K. Sastry, U.-M. O'Reilly, and D. E. Goldberg 9:30 -- 9:55 Parameter Sweeps For Exploring GP Parameters M. E. Samples, J. M. Daida, M. Byom, and M. Pizzimenti 9:55 -- 10:20 Genetic Programming: Parametric Analysis of Structure Altering Mutation Techniques A. Piszcz and T. Soule 10:20 -- 10:40 Coffee Break 10:40 -- 11:05 Investigations in Meta-GAs: Panaceas or Pipe Dreams? J. Clune, S. Goings, B. Punch, and E. Goodman 11:05 -- 11:30 A Review of Adaptive Population Sizing Schemes in Genetic Algorithms F. G. Lobo and C. F. Lima 11:30 -- 11:55 Invited Talk: Online Population Size Adjusting Using Noise and Substructural Measurements T.-L. Yu, K. Sastry, and D. E. Goldberg 11:55 -- 12:30 Panel Discussion [ back to top ] |
||||||||||||||||
| Workshop Chairs | ||||||||||||||||
|
Fernando Lobo and
Claudio Lima Departamento de Engenharia Electrónica e Informática Universidade do Algarve Campus de Gambelas, 8000 Faro Portugal Phone: +351-289-800900 Fax: +351-289-819403 E-mail:   [ back to top ] |
||||||||||||||||
| Program Committee | ||||||||||||||||
[ back to top ] |
||||||||||||||||
| Talk Abstracts | ||||||||||||||||
|
Population Sizing for Genetic Programming Based Upon Decision Making K. Sastry, U.-M. O'Reilly, and D. E. Goldberg We develop a facetwise population-sizing relationship for genetic programming (GP). Following the population-sizing derivation for genetic algorithms in Goldberg, Deb, and Clark (1992), we consider building-block-wise decision making as a key facet. The analysis yields a GP-unique relationship because it has to account for bloat and for the fact that GP solutions often use subsolutions multiple times. The population-sizing relationship depends upon tree size, solution complexity, problem difficulty and building block expression probability. The relationship is used to analyze and empirically investigate population sizing for three model GP problems named ORDER, ON-OFF and LOUD. These problems exhibit bloat to differing extents and differ in whether their solutions require the use of a building block multiple times. Parameter Sweeps For Exploring GP Parameters M. E. Samples, J. M. Daida, M. Byom, and M. Pizzimenti This paper describes our procedure and a software application for conducting large parameter sweep experiments in genetic and evolutionary computation research. Both procedure and software allows a researcher to examine multivariate nonlinearities that are common in genetic and evolutionary computation. Experiments of this nature are well suited to distributed computing environments (such as Grids and clusters) and we present an automated system for conducting parameter sweep experiments on heterogeneous networks. Emphasis is placed on experimental sampling, distributed robustness, and data analysis. The parameter sweep experimental procedure is easily applicable to any experiment involving computer simulations but is particularly well suited for evolutionary computation experiments. Genetic Programming: Parametric Analysis of Structure Altering Mutation Techniques A. Piszcz and T. Soule We hypothesize that the relationship between parameter settings, specifically parameters controlling mutation, and performance is non-linear in genetic programs. Genetic programming environments have few means for a priori determination of appropriate parameters values. The hypothesized nonlinear behavior of genetic programming creates difficulty in selecting parameter values for many problems. In this paper we study three structure altering mutation techniques using parametric analysis on a problem with scalable complexity. We find through parameter analysis that two of the three mutation types tested exhibit nonlinear behavior. Higher mutation rates cause a larger degree of nonlinear behavior as measured by fitness and computational effort. Characterization of the mutation techniques using parametric analysis confirms the nonlinear behavior. In addition, we propose an extension to the existing parameter setting taxonomy to include commonly used structure altering mutation attributes. Finally we show that the proportion of mutations applied to internal nodes, instead of leaf nodes, has a significant effect on performance. Investigations in Meta-GAs: Panaceas or Pipe Dreams? J. Clune, S. Goings, B. Punch, and E. Goodman A meta-GA (GA within a GA) is used to investigate evolving the parameter settings of genetic operators for genetic and evolutionary algorithms (GEA) in the hope of creating a self-adaptive GEA. We report three findings. First, the meta-GA can adapt its genetic operators to different problems and thereby perform well on average across diverse problems. Second, the meta-GA can change its parameters during the course of a run - seemingly a good idea - but this behavior may actually decrease performance. Finally, the genetic operator configurations the meta-GA evolves are far from optimal. We conclude that, while meta-GAs show promise for automating some parameter configurations, they are not likely to replace manually configured genetic and evolutionary algorithms without innovative alteration. A Review of Adaptive Population Sizing Schemes in Genetic Algorithms F. G. Lobo and C. F. Lima This paper reviews the topic of population sizing in genetic algorithms. It starts by revisiting theoretical models which rely on a facetwise decomposition of genetic algorithms, and then moves on to various self-adjusting population sizing schemes that have been proposed in the literature. The paper ends with recommendations for those who design and compare adaptive population sizing schemes for genetic algorithms. Online Population Size Adjusting Using Noise and Substructural Measurements T.-L. Yu, K. Sastry, and D. E. Goldberg This paper proposes an online population size adjustment scheme for genetic algorithms. It utilizes linkage-model-building techniques to calculate the parameters used in facetwise population-sizing models. The methodology is demonstrated using the dependency structure matrix genetic algorithm on a set of boundedly-difficult problems. Empirical results indicate that the proposed method is both efficient and robust. If the initial population size is too large, the proposed method automatically decreases the population size, and thereby yields significant savings in the number of function evaluations required to obtain high-quality solutions; if the initial population size is too small, the proposed scheme increases the population size on-the-fly and thereby avoiding premature convergence. [ back to top ] |
||||||||||||||||
|
|
