A no-free-lunch theorem for non-uniform distributions of target functions

DOI10.1007/s10852-005-2586-yzbMath1079.90111OpenAlexW4236270875MaRDI QIDQ1774632

Christian Igel, Marc Toussaint

Publication date: 17 May 2005

Published in: JMMA. Journal of Mathematical Modelling and Algorithms (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10852-005-2586-y

zbMATH Keywords

evolutionary computationno-free-lunch theorem

Mathematics Subject Classification ID

Combinatorial optimization (90C27) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (17)

Continuous lunches are free plus the design of optimal optimization algorithms ⋮ No Free Lunch Theorems: Limitations and Perspectives of Metaheuristics ⋮ Black-Box Complexity for Bounding the Performance of Randomized Search Heuristics ⋮ The Bayesian Search Game ⋮ Towards objective measures of algorithm performance across instance space ⋮ Across neighborhood search algorithm: a comprehensive analysis ⋮ Free lunches on the discrete Lipschitz class ⋮ Instance spaces for machine learning classification ⋮ A study of search algorithms' optimization speed ⋮ On normalization and algorithm selection for unsupervised outlier detection ⋮ Machine Learning and the Philosophical Problems of Induction ⋮ A framework for co-optimization algorithm performance and its application to worst-case optimization ⋮ No-free-lunch theorems in the continuum ⋮ What Is Important About the No Free Lunch Theorems? ⋮ The impact of parametrization in memetic evolutionary algorithms ⋮ Optimization, block designs and no free lunch theorems ⋮ On the effectiveness of immune inspired mutation operators in some discrete optimization problems

Cites Work

• On classes of functions for which no free lunch results hold
• Neutrality and self-adaptation
• Optimization with randomized search heuristics -- the (A)NFL theorem, realistic scenarios, and difficult functions.

This page was built for publication: A no-free-lunch theorem for non-uniform distributions of target functions