skip to main content
10.1145/1274000.1274103acmconferencesArticle/Chapter ViewAbstractPublication PagesgeccoConference Proceedingsconference-collections
Article

An information perspective on evolutionary computation

Published: 07 July 2007 Publication History

Abstract

This tutorial focuses mainly on Kolmogorov's notion of information that is, the information content of a binary string is the length of the shortest program that can produce this string and halt but more importantly, it concentrates on the applicability of this notion to Optimisation problems and Black-Box algorithms. For example, we will discuss how informal observations of the kind, "ONEMAX contains good information", "NIAH does not contain any" connects with the formal definition.The tutorial covers the following major issues: decomposition of a fitness-function, the entropy of a fitness-function as a bound on the expected performance, Kolmogorov complexity (KC) and its relation to Shannon information theory, KC and problem hardness, the relation between KC and other (applicable) predictive measures to problem difficulty (e.g., auto-correlation, ruggedness) and KC vs. the no-free-lunch theorems.

References

[1]
D.H. Wolpert and W.G. Macready. No free lunch theorems for optimization. IEEE Trans Evolutionary Computation, 4:67--82, 1997.
[2]
C. Schumacher and M. Vose and D. Whitley. The No Free Lunch and Problem Description Length. GECCO 2001.
[3]
W.G. Macready and D.H. Wolpert. What makes an optimization problem hard?. Complex, 1:5:40--46, 1996.
[4]
P. Grünwald and P. Vitanyi. Algorithmic Complexity. Handbook on the Philosophy of Information. To appear.
[5]
T. English. Optimization is Easy and Learning is Hard In the Typical Function. Proc. 2000 Congress on Evolutionary Computation (CEC 2000), pages 924--931, 2000.
[6]
H. Buhrman, M. Li, J. Tromp, P. Vitanyi . Kolmogorov Random Graphs And The Incompressibility Method. SIAM Journal on Computing, 29:590--599.
[7]
Y. Borenstein, R. Poli. Kolmogorov complexity, Optimization and Hardness, IEEE CEC 2006.
[8]
Y. Borenstein, R. Poli. Information Perspective of Optimization. PPSN 2006: 102--111.
[9]
Y. Borenstein. What Makes an Optimization Problem Hard? An Information-Theoretic Perspective. PhD Thesis, Chapter 3.

Index Terms

  1. An information perspective on evolutionary computation

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    GECCO '07: Proceedings of the 9th annual conference companion on Genetic and evolutionary computation
    July 2007
    1450 pages
    ISBN:9781595936981
    DOI:10.1145/1274000
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 07 July 2007

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Kolmogorov complexity
    2. evolutionary computation
    3. theory

    Qualifiers

    • Article

    Conference

    GECCO07
    Sponsor:
    GECCO07: Genetic and Evolutionary Computation Conference
    July 7 - 11, 2007
    London, United Kingdom

    Acceptance Rates

    Overall Acceptance Rate 1,669 of 4,410 submissions, 38%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 155
      Total Downloads
    • Downloads (Last 12 months)0
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media