HypBO: Accelerating Black-Box Scientific Experiments Using Experts' Hypotheses

TL;DR

HypBO leverages expert hypotheses to guide Bayesian optimization, significantly accelerating scientific experiments like chemical discovery by improving seed sampling and search efficiency.

Contribution

The paper introduces HypBO, a novel method that incorporates expert hypotheses into Bayesian optimization to enhance search speed in scientific problems.

Findings

HypBO outperforms traditional Bayesian optimization in synthetic tests.

Using expert hypotheses accelerates chemical design tasks.

HypBO effectively filters unpromising seeds to focus on promising regions.

Abstract

Robotics and automation offer massive accelerations for solving intractable, multivariate scientific problems such as materials discovery, but the available search spaces can be dauntingly large. Bayesian optimization (BO) has emerged as a popular sample-efficient optimization engine, thriving in tasks where no analytic form of the target function/property is known. Here, we exploit expert human knowledge in the form of hypotheses to direct Bayesian searches more quickly to promising regions of chemical space. Previous methods have used underlying distributions derived from existing experimental measurements, which is unfeasible for new, unexplored scientific tasks. Also, such distributions cannot capture intricate hypotheses. Our proposed method, which we call HypBO, uses expert human hypotheses to generate improved seed samples. Unpromising seeds are automatically discounted, while promising seeds are used to augment the surrogate model data, thus achieving better-informed sampling. This process continues in a global versus local search fashion, organized in a bilevel optimization framework. We validate the performance of our method on a range of synthetic functions and demonstrate its practical utility on a real chemical design task where the use of expert hypotheses accelerates the search performance significantly.