No Free Lunch Theorems for Search (1995) [188 citations — 2 self]
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
author = {David H. Wolpert and William G. Macready and David H and William G},
title = {No Free Lunch Theorems for Search},
year = {1995}
}
Bookmarks
OpenURL
Abstract:
We show that all algorithms that search for an extremum of a cost function perform exactly the same, when averaged over all possible cost functions. In particular, if algorithm A outperforms algorithm B on some cost functions, then loosely speaking there must exist exactly as many other functions where B outperforms A. Starting from this we analyze a number of the other a priori characteristics of the search problem, like its geometry and its information-theoretic aspects. This analysis allows us to derive mathematical benchmarks for assessing a particular search algorithm 's performance. We also investigate minimax aspects of the search problem, the validity of using characteristics of a partial search over a cost function to predict future behavior of the search algorithm on that cost function, and time-varying cost functions. We conclude with some discussion of the justifiability of biologically-inspired search methods. 1 Introduction Many problems can be cast as optimization over ...
Citations
| 4923 | Elements of Information Theory – Cover, Thomas - 1991 |
| 1942 | Adaptation in Natural and Artificial Systems – Holland - 1975 |
| 464 | Heuristics: Intelligent Search Strategies for Computer Problem Solving – Pearl - 1984 |
| 29 | On overfitting avoidance as bias – Wolpert - 1993 |
| 19 | Off-training set error and a priori distinctions between learning algorithms – Wolpert - 1995 |
| 10 | de la Maza M. Dynamic Hill Climbing: Overcoming the limitations of optimization techniques – Yuret, M - 1993 |
| 2 | Reinelt, The Traveling Salesman, computational solutions for TSP applications – Gerhard - 1994 |
