Is there any methodology to find proper parameter settings for a given meta-heuristic algorithm, e.g. the firefly algorithm or the cuckoo search? Is this an open issue in optimization? Is extensive experimentation, measurements and intuition the only way to figure out which are the best settings?
How to find the best configuration for an algorithm is an open research question in AI. The topic in general is known as `hyper-parameter optimization' and there are a range of possible methods:
One of the most popular is IRace, but other possibilities include:
Spearmint: uses wrappers in Matlab or Python. It uses MongoDb, and Bayesian optimisation algorithms.
SMAC requires a python wrapper for the algorithm to be optimized and has a command line interface.
Hyperopt: a Python library which uses Random Search and Tree of Parzen Estimators.
This paper argues that Spearmint performs the best, compared with SMAC and Hyperopt, but with significantly longer running times in some cases.