A General Framework for User-Guided Bayesian Optimization
This addresses the problem for knowledgeable practitioners in scientific disciplines with tight budgets by enabling user-guided optimization, though it is incremental as it builds on existing Bayesian optimization methods.
The paper tackles the limitation of Bayesian optimization in incorporating user prior beliefs to accelerate optimization, proposing ColaBO, a framework that allows customization and shows substantial acceleration when prior information is accurate while maintaining performance when it is misleading.
The optimization of expensive-to-evaluate black-box functions is prevalent in various scientific disciplines. Bayesian optimization is an automatic, general and sample-efficient method to solve these problems with minimal knowledge of the underlying function dynamics. However, the ability of Bayesian optimization to incorporate prior knowledge or beliefs about the function at hand in order to accelerate the optimization is limited, which reduces its appeal for knowledgeable practitioners with tight budgets. To allow domain experts to customize the optimization routine, we propose ColaBO, the first Bayesian-principled framework for incorporating prior beliefs beyond the typical kernel structure, such as the likely location of the optimizer or the optimal value. The generality of ColaBO makes it applicable across different Monte Carlo acquisition functions and types of user beliefs. We empirically demonstrate ColaBO's ability to substantially accelerate optimization when the prior information is accurate, and to retain approximately default performance when it is misleading.