A note on the maximum missed-opportunity cost incurred by minimizing expected losses in genetic algorithms

The foundational analysis of genetic algorithms in terms of sampling from s chemata relies on minimizing expected losses. This criterion does not corre spond with the problem of finding the single solution to a problem that aff ords the best quality. Analysis developed here indicates the maximum cost t hat might be realized by a search strategy that minimizes expected losses w hen sampling from non-negative random variables.