Journal article

Generating New Space-Filling Test Instances for Continuous Black-Box Optimization

Mario A Munoz, Kate Smith-Miles



This article presents a method to generate diverse and challenging new test instances for continuous black-box optimization. Each instance is represented as a feature vector of exploratory landscape analysis measures. By projecting the features into a two-dimensional instance space, the location of existing test instances can be visualized, and their similarities and differences revealed. New instances are generated through genetic programming which evolves functions with controllable characteristics. Convergence to selected target points in the instance space is used to drive the evolutionary process, such that the new instances span the entire space more comprehensively. We demonstrate the..

View full abstract


Awarded by Australian Research Council through the Australian Laureate Fellowship

Funding Acknowledgements

Both authors were with School of Mathematical Sciences, Monash University, Clayton, VIC 3800, Australia, while conducting the experimental part of this work. Funding was provided by the Australian Research Council through the Australian Laureate Fellowship FL140100012. We also thank Dr. Toan Nguyen, who implemented optimized versions of the metafeatures routines, and Philip Chan, who set up access to additional computational resources for the ten-dimensional function generations.