The True Destination of EGO is Multi-local Optimization
This work addresses the practical limitations of a popular optimization algorithm for researchers and practitioners in fields like engineering and machine learning, offering an incremental improvement by re-evaluating its strengths in multi-local optimization.
The paper tackles the problem of efficiently optimizing expensive multimodal black-box functions, showing experimentally that the Efficient Global Optimization algorithm is more effective for identifying multiple optima rather than relying on its theoretical global convergence properties.
Efficient global optimization is a popular algorithm for the optimization of expensive multimodal black-box functions. One important reason for its popularity is its theoretical foundation of global convergence. However, as the budgets in expensive optimization are very small, the asymptotic properties only play a minor role and the algorithm sometimes comes off badly in experimental comparisons. Many alternative variants have therefore been proposed over the years. In this work, we show experimentally that the algorithm instead has its strength in a setting where multiple optima are to be identified.