Panel Discussion

Yin-Yang: No-Free-Lunch
Theorems for Search

at the

1995 International Conference on Genetic Algorithms (ICGA-95)

15-19 July, 1995
University of Pittsburgh
Pittsburgh, PA USA

Panel Members:
William M. Spears (Moderator)
Kenneth De Jong
William Macready
Michael Vose
Darrell Whitley

Yin-Yang reflects the philosophy that for every positive there is a negative. The No-Free-Lunch theorems of David Wolpert and William Macready capture this philosophy formally with respect to induction and search. This panel discussed these results in detail - namely, the mathematical model underlying the NFL theorems, a formal statement of the results, and what these results tell us about various issues in genetic algorithms. The panel discussion occurred on Monday, July 17, from 3:50 pm - 5:30 pm. Thanks to Bill Macready for an excellent overview of the NFL work. Some relevant papers (in alphabetical order by first author) are below.

Culberson, J. (1996), "On the Futility of Blind Search"

English, T. (1997), "Various Papers on Conservation"

Macready, W. and D. Wolpert (1995), "What Makes an Optimization Problem Hard?"

Radcliffe, N. and P. Surry (1995), "Fundamental Limitations on Search Algorithms: Evolutionary Computing in Practice"

Rao, R. B., Gordon, D. F. and W. M. Spears (1995), "For Every Generalization Action, Is There Really an Equal and Opposite Reaction? Analysis of the Conservation Law of Generalization Performance"

Schaffer, C. (1994), "A Conservation Law for Generalization Performance"

Schaffer, C. (1995), "Conservation of Generalization: A Case Study (draft)"

Spears, W. M., and K. A. De Jong (1998), "Dining with GAs: Operator Lunch Theorems"

Wolpert, D. and W. Macready (1994), "No Free Lunch Theorems for Search"

Wolpert, D. and W. Macready (1997), "No Free Lunch Theorems for Optimization"

Wolpert, D. (1991), "Off-training Set Error and a Priori Distinctions Between Learning Algorithms"

There is also a Web page for NFL discussions. Click here for details





For more information, please contact William M. Spears.
Last modified: 07/29/99