Race to the bottom: Bayesian optimisation for chemical problems

What is the minimum number of experiments, or calculations, required to find an optimal solution? Relevant chemical problems range from identifying a compound with target functionality within a given phase space to controlling materials synthesis and device fabrication conditions. A common feature in this application domain is that both the dimensionality of the problems and the cost of evaluations are high. The selection of an appropriate optimisation technique is key, with standard choices including iterative (e.g. steepest descent) and heuristic (e.g. simulated annealing) approaches, which are complemented by a new generation of statistical machine learning methods. Here we pay attention to progress in Bayesian optimisation. We highlight recent success cases and discuss the challenges of using machine learning with automated research workflows that produce small and noisy data sets. Finally, we outline opportunities for developments in hybrid algorithms for robust and efficient searches.