Continuous lunches are free!

This paper investigates extensions of No Free Lunch (NFL) theorems to countably infinite and uncountable infinite domains. The original NFLdue to Wolpert and Macready states that all search heuristics have the same performance when averaged over the uniform distribution over all possible functions. For infinite domains the extension of the concept of distribution over all possible functions involves measurability issues and stochastic process theory. For countably infinite domains, we prove that the natural extension of NFL theorems does not hold, but that a weaker form of NFL does hold, by stating the existence of non-trivial distributions of fitness leading to equal performance forall search heuristics. Our main result is that for continuous domains, NFL does not hold.

[1]  Patrick Billingsley,et al.  Probability and Measure. , 1986 .

[2]  Thomas Jansen,et al.  Optimization with randomized search heuristics - the (A)NFL theorem, realistic scenarios, and difficult functions , 2002, Theor. Comput. Sci..

[3]  Joshua D. Knowles,et al.  Some multiobjective optimizers are better than others , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[4]  Marc Toussaint,et al.  A No-Free-Lunch Theorem for Non-Uniform Distributions of Target Functions , 2004 .

[5]  J. Doob Stochastic process measurability conditions , 1975 .

[6]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[7]  Erik H. Vanmarcke,et al.  Random Fields: Analysis and Synthesis. , 1985 .

[8]  P. Spreij Probability and Measure , 1996 .

[9]  L. D. Whitley,et al.  The No Free Lunch and problem description length , 2001 .

[10]  Joseph C. Culberson,et al.  On the Futility of Blind Search: An Algorithmic View of No Free Lunch , 1998, Evolutionary Computation.

[11]  Patrick D. Surry,et al.  Fundamental Limitations on Search Algorithms: Evolutionary Computing in Perspective , 1995, Computer Science Today.

[12]  Paul Jung,et al.  No free lunch. , 2002, Health affairs.

[13]  P. J. Daniell Integrals in An Infinite Number of Dimensions , 1919 .

[14]  Thomas Jansen,et al.  Design and Management of Complex Technical Processes and Systems by Means of Computational Intelligence Methods Perhaps Not a Free Lunch but at Least a Free Appetizer Perhaps Not a Free Lunch but at Least a Free Appetizer , 2022 .

[15]  A. N. Kolmogorov,et al.  Foundations of the theory of probability , 1960 .