BoTier: multi-objective Bayesian optimization with tiered objective structures

Abstract

Scientific optimization problems are usually concerned with balancing multiple competing objectives that express preferences over both the outcomes of an experiment (e.g. maximize reaction yield) and the corresponding input parameters (e.g. minimize the use of an expensive reagent). In practice, operational and economic considerations often establish a hierarchy of these objectives, which must be reflected in algorithms for sample-efficient experiment planning. Herein, we introduce BoTier, a software library that can flexibly represent a hierarchy of preferences over experiment outcomes and input parameters. We provide systematic benchmarks on synthetic and real-life surfaces, demonstrating the robust applicability of BoTier across a number of use cases. Importantly, BoTier is implemented in an auto-differentiable fashion, enabling seamless integration with the BoTorch library, thereby facilitating adoption by the scientific community.