Multi-Objective Bayesian Optimization over High-Dimensional Search Spaces
This addresses a scalability bottleneck for practitioners in scientific and industrial applications like optical display and vehicle design, offering a significant but incremental advance over prior methods.
The paper tackles the problem of scaling multi-objective Bayesian optimization to high-dimensional search spaces, where existing methods perform poorly, and proposes MORBO, which achieves order-of-magnitude improvements in sample efficiency on synthetic and real-world problems with up to 222 parameters.
Many real world scientific and industrial applications require optimizing multiple competing black-box objectives. When the objectives are expensive-to-evaluate, multi-objective Bayesian optimization (BO) is a popular approach because of its high sample efficiency. However, even with recent methodological advances, most existing multi-objective BO methods perform poorly on search spaces with more than a few dozen parameters and rely on global surrogate models that scale cubically with the number of observations. In this work we propose MORBO, a scalable method for multi-objective BO over high-dimensional search spaces. MORBO identifies diverse globally optimal solutions by performing BO in multiple local regions of the design space in parallel using a coordinated strategy. We show that MORBO significantly advances the state-of-the-art in sample efficiency for several high-dimensional synthetic problems and real world applications, including an optical display design problem and a vehicle design problem with 146 and 222 parameters, respectively. On these problems, where existing BO algorithms fail to scale and perform well, MORBO provides practitioners with order-of-magnitude improvements in sample efficiency over the current approach.