CiteSeerX — No free lunch theorems for optimization

No free lunch theorems for optimization (1997) [375 citations — 5 self]

Popular Tags

No tags have been applied to this document.

BibTeX | Add To MetaCart

@ARTICLE{Wolpert97nofree,
    author = {David H. Wolpert and William G. Macready},
    title = {No free lunch theorems for optimization},
    journal = {IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION},
    year = {1997},
    volume = {1},
    number = {1},
    pages = {67--82}
}

Years of Citing Articles

Bookmarks

OpenURL

Abstract:

A framework is developed to explore the connection between effective optimization algorithms and the problems they are solving. A number of “no free lunch” (NFL) theorems are presented which establish that for any algorithm, any elevated performance over one class of problems is offset by performance over another class. These theorems result in a geometric interpretation of what it means for an algorithm to be well suited to an optimization problem. Applications of the NFL theorems to information-theoretic aspects of optimization and benchmark measures of performance are also presented. Other issues addressed include time-varying optimization problems and a priori “head-to-head” minimax distinctions between optimization algorithms, distinctions that result despite the NFL theorems' enforcing of a type of uniformity over all algorithms

Citations

4923	Elements of Information Theory – Cover, Thomas - 1991
2331	Optimization by Simulated Annealing – Kirkpatrick, Gelatt, et al. - 1983
1942	Adaptation in Natural and Artificial Systems – Holland - 1975
470	Artificial Intelligence Through A Simulation of Evolution – Fogel, Owens, et al. - 1965
188	No Free Lunch Theorems for Search – Wolpert - 1995
122	Adaptation in Natural and Arti cial Systems – Holland - 1975
38	Markov Random Fields and Their Applications – Kinderman, Snell - 1980
21	Arti cial Intelligence Through Simulated Evolution – Fogel, Owens, et al. - 1966
7	Introduction to Random Fields – Griffeath - 1976
5	The lack of a prior distinctions between learning algorithms and the existence of a priori distinctions between learning algorithms – Wolpert - 1996
3	What makes an optimization problem – Macready, Wolpert - 1996
3	No free lunch theorems for search. Technical Report SFI-TR-05-010; ftp : ==ftp:santafe:edu=pub=dhw f tp=nf l:search:T R:ps:Z, Santa Fe Institute – Wolpert, Macready - 1995
2	Markov random elds and their applications – Kindeman, Snell - 1990
1	Gri eath. Introduction to random elds – unknown authors - 1976