(179b) From Theory to Impact: Unlocking the Power of Bayesian Optimization on Real-World Science and Engineering Systems

Bayesian optimization (BO) is a powerful tool for optimizing non-convex black-box functions that are expensive and/or time-consuming to evaluate and may be subject to stochastic noise in their evaluations. Many important problems can be formulated in this manner, such as optimizing outcomes of high-fidelity computer simulations, hyperparameter tuning in machine learning algorithms, A/B testing for website design, policy-based reinforcement learning, process flowsheet synthesis, and material and drug discovery. In this presentation, three key concepts are introduced, which we argue are critical for enabling or improving the performance of BO on real-world science and engineering systems. Specifically, one must: (1) leverage prior (physics-based) knowledge to perform highly efficient, targeted exploration of the solution space; (2) explicitly incorporate safety constraints during interaction with physical systems to avoid unsafe/undesirable outcomes; and (3) account for external uncertainty sources to ensure the best-found solution is robust/flexible in practice. We introduce a unified framework for adapting BO to handle these considerations and illustrate how this framework can be deployed in practice on a series of examples ranging from the design of safe cold plasma jet devices to the discovery of high-performance sustainable energy storage materials. We also offer perspectives on key challenges and future opportunities in the realm of applied BO.