A Survey of Methods for Automated Algorithm Configuration
This survey provides a structured overview for researchers and practitioners in algorithm configuration, but it is incremental as it builds on existing reviews by adding new taxonomies.
The paper tackles the lack of comprehensive reviews in automated algorithm configuration by introducing taxonomies to classify problem variants and methods, and uses these to review existing literature, outline design choices, and describe industry applications.
Algorithm configuration (AC) is concerned with the automated search of the most suitable parameter configuration of a parametrized algorithm. There is currently a wide variety of AC problem variants and methods proposed in the literature. Existing reviews do not take into account all derivatives of the AC problem, nor do they offer a complete classification scheme. To this end, we introduce taxonomies to describe the AC problem and features of configuration methods, respectively. We review existing AC literature within the lens of our taxonomies, outline relevant design choices of configuration approaches, contrast methods and problem variants against each other, and describe the state of AC in industry. Finally, our review provides researchers and practitioners with a look at future research directions in the field of AC.