Can you recommend papers that prove theoretically that different versions of metaheuristic algorithms are actually giving similar performance? So far I have looked at the No Free Lunch (NFL) theorem and also read some papers that compare the performances, but these papers only report empirical results.
Maybe this article help you.
https://link.springer.com/article/10.1007/s101070100263
I am not familiar with theoretical comparisons of particular algorithms. Yet, if you are interested in recent empirical ones then you may find some limited comparisons on a neuro-control problem in:
Salih, Adham, and Amiram Moshaiov. "Multi-objective neuro-evolution: Should the main reproduction mechanism be crossover or mutation?." Systems, Man, and Cybernetics (SMC), 2016 IEEE International Conference on. IEEE, 2016.
.We are currently working on extending the paper to some other benchmark problems.
- Badges
- Science topic
- Similar topics
- Philosophy
- Moral Philosophy
- Free Will