Explainable Landscape-Aware Optimization Performance Prediction
This work addresses the problem of explainability in algorithm selection for optimization practitioners, but it is incremental as it builds on existing landscape-aware prediction methods.
The study tackled the limited explainability of automated optimization algorithm performance prediction models by developing explainable landscape-aware regression models that estimate the contribution of each landscape feature globally and locally. The results, using COCO benchmark problems and CMA-ES variants, demonstrated that different features are important for different problem instances, indicating a need for personalized landscape space training.
Efficient solving of an unseen optimization problem is related to appropriate selection of an optimization algorithm and its hyper-parameters. For this purpose, automated algorithm performance prediction should be performed that in most commonly-applied practices involves training a supervised ML algorithm using a set of problem landscape features. However, the main issue of training such models is their limited explainability since they only provide information about the joint impact of the set of landscape features to the end prediction results. In this study, we are investigating explainable landscape-aware regression models where the contribution of each landscape feature to the prediction of the optimization algorithm performance is estimated on a global and local level. The global level provides information about the impact of the feature across all benchmark problems' instances, while the local level provides information about the impact on a specific problem instance. The experimental results are obtained using the COCO benchmark problems and three differently configured modular CMA-ESs. The results show a proof of concept that different set of features are important for different problem instances, which indicates that further personalization of the landscape space is required when training an automated algorithm performance prediction model.