Inferring arbitrary quantities of interest (QoI) using limited computational or, in realistic
scenarios, financial budgets, is a challenging problem that requires sophisticated strategies …

Bayesian optimisation is a well-known sample-efficient method for the optimisation of
expensive black-box functions. However when dealing with big search spaces the algorithm …

Traditional methods for kernel selection rely on parametric kernel functions or a combination
thereof and although the kernel hyperparameters are tuned, these methods often provide …

Gradient Langevin dynamics (GLD) and stochastic GLD (SGLD) have attracted considerable
attention lately, as a way to provide convergence guarantees in a non-convex setting …

This research focuses on how AI systems can team with expert scientists and engineers to
quicken the discovery of new knowledge, products and processes. This thesis investigates …

The scale-up of laboratory procedures to industrial production is the main challenge
standing between ideation and the successful introduction of novel materials into …

Bayesian optimisation is a widely used technique for finding the optima of black-box
functions in a sample efficient way. When there are concurrent optimisation tasks/functions …