Research

My core research revolves around decision-making under uncertainty with physics-inspired machine learning. More concretely, I am interested in how we can leverage probabilistic models with physical constraints (e.g., physics-informed Gaussian processes, probabilistic numerics) to devise decision rules (e.g., active learning, Bayesian optimisation), often under practical limitations such as restricted search domains, non-standard measurement devices, or computational budgets.

Currently, I am investigating spatio-temporal active learning for the deployment of oceanographic sensors. I am also actively exploring the decision-making aspects of probabilistic numerics.

Publication

Google Scholar

Preprints

  • Iguchi, Y., Livingstone, S., Nüsken, N., Vasdekis, G., & Zhang, R. Y. (2025). Skew-symmetric schemes for stochastic differential equations with non-Lipschitz drift: an unadjusted Barker algorithm. [arxiv] [code] (submitted)

Publications and Workshop Papers

  • Zhang, R. Y., Moss, H. B., Astfalck, L. C., Cripps, E. J., and Leslie, D. S. (2024). BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories. NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty. [OpenReview] [slides] [talk]