Gbachelier am 14. November 2014 um 16:33 Uhr

2014-11-14T16:33:29Z

Gbachelier: Die Seite wurde neu angelegt: „ == Reference == Wolpert, D.H., Macready, W.G. (1997). No free lunch theorems for search. IEEE Transactions on Evolutionary Computation, 1(1): 67–82. == D…“

2014-11-14T16:12:53Z

Die Seite wurde neu angelegt: „ == Reference == Wolpert, D.H., Macready, W.G. (1997). No free lunch theorems for search. IEEE Transactions on Evolutionary Computation, 1(1): 67–82. == D…“

Neue Seite

== Reference ==
Wolpert, D.H., Macready, W.G. (1997). No free lunch theorems for search. IEEE Transactions on Evolutionary Computation, 1(1): 67–82.

== DOI ==
http://dx.doi.org/10.1109/4235.585893

== 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

== Extended Abstract ==

== Bibtex ==

== Used References ==
L. J. Fogel, A. J. Owens, and M. J. Walsh, Artificial Intelligence Through Simulated Evolution, 1966 :Wiley

J. H. Holland, Adaptation in Natural and Artificial Systems, 1993 :MIT Press

H.-P. Schwefel, Evolution and Optimum Seeking, 1995 :Wiley

S. Kirkpatrick, D. C. Gelatt, and M. P. Vecchi, "Optimization by simulated annealing", Science, vol. 220, pp.671 -680 1983 http://dx.doi.org/10.1126/science.220.4598.671

W. G. Macready and D. H. Wolpert, "What makes an optimization problem hard?", Complexity, vol. 5, pp.40 -46 1996

D. H. Wolpert and W. G. Macready, No free lunch theorems for search, 1995 :Santa Fe Institute

F. Glover, "Tabu search I", ORSA J. Comput., vol. 1, pp.190 -206 1989 http://dx.doi.org/10.1287/ijoc.1.3.190

F. Glover, "Tabu search II", ORSA J. Comput., vol. 2, pp.4 -32 1990

E. L. Lawler and D. E. Wood, "Branch and bound methods: A survey", Oper. Res., vol. 14, pp.699 -719 1966 http://dx.doi.org/10.1287/opre.14.4.699

R. Kinderman and J. L. Snell, Markov Random Fields and Their Applications, 1980 :Amer. Math. Soc.

D. H. Wolpert, "The lack of a prior distinctions between learning algorithms", Neural Computation, vol. 8, pp.1341 -1390 1996 http://dx.doi.org/10.1162/neco.1996.8.7.1341

D. H. Wolpert, "On bias plus variance", Neural Computation, vol. 9, pp.1271 -1248 1996

D. Griffeath, J. G. Kemeny, J. L. Snell, and A. W. Knapp, "Introduction to random fields", Denumerable Markov Chains, 1976 :Springer-Verlag

C. E. M. Strauss, D. H. Wolpert, and D. R. Wolf, "Alpha, evidence, and the entropic prior", Maximum Entropy and Bayesian Methods, pp.113 -120 1992 :Addison-Wesley

T. M. Cover and J. A. Thomas, Elements of Information Theory, 1991 :Wiley http://dx.doi.org/10.1002/0471200611

== Links ==
=== Full Text ===

[[intern file]]

=== Sonstige Links ===
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.39.6926

http://www.cs.ubc.ca/~hutter/earg/papers07/00585893.pdf No Free Lunch Theorems for Optimization

@@ Zeile 2: / Zeile 2: @@
 == Reference ==
-Wolpert, D.H., Macready, W.G. (1997). No free lunch theorems for search. IEEE Transactions on Evolutionary Computation, 1(1): 67–82.
+Wolpert, D.H., Macready, W.G. (1995). No free lunch theorems for search.  SFI-TR-95-02-010 Santa Fe Institute 1995
 == DOI ==
-http://dx.doi.org/10.1109/4235.585893
 == 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
+We show that all algorithms that search for an extremum of a cost
 == Extended Abstract ==
@@ Zeile 15: / Zeile 26: @@
 == Used References ==
-L. J. Fogel, A. J. Owens, and M. J. Walsh,  Artificial Intelligence Through Simulated Evolution,  1966 :Wiley
+] M.R. Garey, D.S. Johnson, Computers and Intractability, Freeman (1979).
-H.-P. Schwefel,  Evolution and Optimum Seeking,  1995 :Wiley
+] E.L. Lawler, D.E. Wood, Operations Research, 14(4), 699-719, (1966).
-S. Kirkpatrick, D. C. Gelatt, and M. P. Vecchi,  "Optimization by simulated annealing",  Science,  vol. 220,  pp.671 -680 1983 http://dx.doi.org/10.1126/science.220.4598.671
+] J. Pearl, Heuristics, intelligent search strategies for computer problem solv-
-W. G. Macready and D. H. Wolpert,  "What makes an optimization problem hard?",  Complexity,  vol. 5,  pp.40 -46 1996
+] S. Kirkpatrick, C. D. Gelatt Jr., M. P. Vecchi, Science, 220, 671, (1983).
-D. H. Wolpert and W. G. Macready,  No free lunch theorems for search,  1995 :Santa Fe Institute
+] J. Holland, Adaptation in Natural and Arti cial Systems, University of
-F. Glover,  "Tabu search I",  ORSA J. Comput.,  vol. 1,  pp.190 -206 1989 http://dx.doi.org/10.1287/ijoc.1.3.190
+] L. Ingber, Adaptive Simulated Annealing, Software package documenta-
-F. Glover,  "Tabu search II",  ORSA J. Comput.,  vol. 2,  pp.4 -32 1990
+] D. Yuret, M. de la Maza, Dynamic Hill-Climbing: Overcoming the limi-
-E. L. Lawler and D. E. Wood,  "Branch and bound methods: A survey",  Oper. Res.,  vol. 14,  pp.699 -719 1966 http://dx.doi.org/10.1287/opre.14.4.699
+] C.E.M. Strauss, D.H. Wolpert, D.R. Wolf. Alpha, Evidence, and the
-R. Kinderman and J. L. Snell,  Markov Random Fields and Their Applications,  1980 :Amer. Math. Soc.
+] T. Cover, J. Thomas, Elements of Information Theory, John Wiley &
-D. H. Wolpert,  "The lack of a prior distinctions between learning algorithms",  Neural Computation,  vol. 8,  pp.1341 -1390 1996 http://dx.doi.org/10.1162/neco.1996.8.7.1341
+] D H. Wolpert, O -training set error and a priori distinctions between
-D. H. Wolpert,  "On bias plus variance",  Neural Computation,  vol. 9,  pp.1271 -1248 1996
+] D H. Wolpert, On Over tting Avoidance as Bias, Technical Report SFI-
-D. Griffeath,  J. G. Kemeny, J. L. Snell, and A. W. Knapp,  "Introduction to random fields",  Denumerable Markov Chains,  1976 :Springer-Verlag
+] Gerhard Reinelt, The Traveling Salesman, computational solutions for
-C. E. M. Strauss, D. H. Wolpert, and D. R. Wolf,  "Alpha, evidence, and the entropic prior",  Maximum Entropy and Bayesian Methods,  pp.113 -120 1992 :Addison-Wesley
+] P.F. Stadler, Europhys. Lett. 20, pp479-482, (1992).
 == Links ==
 === Full Text ===
+http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.33.5447&rep=rep1&type=pdf
 [[intern file]]
 === Sonstige Links ===
-http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.39.6926
+http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.5447&rank=1

No free lunch theorems for search - Versionsgeschichte

Gbachelier am 14. November 2014 um 16:33 Uhr

Gbachelier: Die Seite wurde neu angelegt: „ == Reference == Wolpert, D.H., Macready, W.G. (1997). No free lunch theorems for search. IEEE Transactions on Evolutionary Computation, 1(1): 67–82. == D…“