Leveraging benchmarking data for informed one-shot dynamic algorithm selection

A key challenge in the application of evolutionary algorithms in practice is the selection of an algorithm instance that best suits the problem at hand. What complicates this decision further is that different algorithms may be best suited for different stages of the optimization process. Dynamic algorithm selection and configuration are therefore well-researched topics in evolutionary computation. Two different settings are classically considered: hyper-heuristics and parameter control studies typically assume a setting in which the algorithm needs to be chosen and adjusted during the run, without prior information, other approaches such as hyper-parameter tuning and automated algorithm configuration assume the possibility of evaluating different configurations before making a final recommendation. In practical applications of evolutionary algorithms we are often in a middle-ground between these two settings, where one needs to decide upon the algorithm instance before the run ("oneshot" setting), but where we have (possibly lots of) data available on which we can base an informed decision. We analyze in this work how such prior performance data can be used to infer informed dynamic algorithm selection schemes for the solution of pseudo-Boolean optimization problems. Our specific use-case considers a family of genetic algorithms.