Continuous lunches are free!

Anne Auger 1 Olivier Teytaud 1
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : This paper investigates extensions of No Free Lunch (NFL) theorems to countably infinite and uncountable infinite do- mains. The original NFL due 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 measur- ability 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 distribution of fitness leading to equal performance for all search heuristics. Our main result is that for continuous domains, NFL does not hold.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download
Contributor : Olivier Teytaud <>
Submitted on : Wednesday, September 19, 2007 - 3:40:11 PM
Last modification on : Wednesday, March 27, 2019 - 4:41:29 PM
Long-term archiving on : Thursday, April 8, 2010 - 10:00:05 PM


Files produced by the author(s)


  • HAL Id : inria-00173209, version 1



Anne Auger, Olivier Teytaud. Continuous lunches are free!. GECCO, 2007, London, United Kingdom. ⟨inria-00173209⟩



Record views


Files downloads