Explainable Landscape-Aware Optimization Performance Prediction

Abstract

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.

Explainable Landscape Analysis in Automated Algorithm Performance Prediction

“…In addition, it has been shown that personalizing the regression models to the problem instance that is being solved can decrease the predictive error [2]. Furthermore, a recent study provides global (across all benchmark problem instances) and local (for a single problem instance) explanations of which ELA features are most important when a supervised ML algorithm is used to predict an optimization algorithm performance [22]. However, these explanations have not been analyzed when different supervised ML methods are used in the predictive task.…”