Change search
ReferencesLink to record
Permanent link

Direct link
Free Lunch for Optimisation under the Universal Distribution
Stockholm University, Faculty of Science, Department of Mathematics.ORCID iD: 0000-0002-7168-4871
2014 (English)In: 2014 IEEE CongressĀ on Evolutionary Computation (CEC), New York: IEEE Computer Society, 2014, 167-174 p.Conference paper (Refereed)
Abstract [en]

Function optimisation is a major challenge in computer science. The No Free Lunch theorems state that if all functions with the same histogram are assumed to be equally probable then no algorithm outperforms any other in expectation. We argue against the uniform assumption and suggest a universal prior exists for which there is a free lunch, but where no particular class of functions is favoured over another. We also prove upper and lower boundson the size of the free lunch.

Place, publisher, year, edition, pages
New York: IEEE Computer Society, 2014. 167-174 p.
Keyword [en]
No free Lunch, Black-box optimisation, universal distribution, Solomonoff induction, Kolmogorov complexity
National Category
Computer Science Algebra and Logic Robotics
Research subject
Computer Science; Mathematics
URN: urn:nbn:se:su:diva-112781ISI: 000356684600024ISBN: 978-1-4799-1488-3OAI: diva2:780777
IEEE Congress on Evolutionary Computation (CEC), July 6-11, 2014, Beijing, People's Republic of China
Available from: 2015-01-15 Created: 2015-01-15 Last updated: 2015-08-17Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Everitt, Tom
By organisation
Department of Mathematics
Computer ScienceAlgebra and LogicRobotics

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 9 hits
ReferencesLink to record
Permanent link

Direct link