Good practices for Bayesian Optimization of high dimensional structured spaces
This work offers practical guidelines for practitioners applying Bayesian Optimization to high-dimensional structured data, addressing a gap between methodological advancements and real-world application needs.
This paper investigates Bayesian Optimization (BO) in high-dimensional structured spaces, focusing on how different design choices for the search space impact performance. It analyzes the effects of latent space dimensionality, acquisition functions, and automatic bound definition, providing practical recommendations.
The increasing availability of structured but high dimensional data has opened new opportunities for optimization. One emerging and promising avenue is the exploration of unsupervised methods for projecting structured high dimensional data into low dimensional continuous representations, simplifying the optimization problem and enabling the application of traditional optimization methods. However, this line of research has been purely methodological with little connection to the needs of practitioners so far. In this paper, we study the effect of different search space design choices for performing Bayesian Optimization in high dimensional structured datasets. In particular, we analyse the influence of the dimensionality of the latent space, the role of the acquisition function and evaluate new methods to automatically define the optimization bounds in the latent space. Finally, based on experimental results using synthetic and real datasets, we provide recommendations for the practitioners.