Summary

I am doing a PhD in the Department of Applied Mathematics and Theoretical Physics (DAMTP) as part of Machine Learning and AI for Medicine group led by Prof. Mihaela van der Schaar. My research focus is on deep machine learning methods for continuous-time control, this encompasses new forms of model-based reinforcement learning for robotics tasks. Specifically this includes developing state-of-the-art time series forecasting models and state-of-the-art model-based reinforcement learning frameworks, that include deterministic and probabilistic models that can be applied to ML for health and science applications. Tangentially, I also have research interests and a publication in model-free reinforcement learning with generative models for applied science, to discover the underlying physical equations from a dataset (symbolic regression).

Background

• 2020 -  Now : PhD in Machine Learning at DAMTP
• 2013 - 2017 : MEng in Engineering Science (High 1st class)

Selected publications

• Samuel I Holt, Zhaozhi Qian, and Mihaela van der Schaar. Neural Laplace: Learning diverse classes of differential equations in the Laplace domain. In International Conference on Machine Learning, pp. 8811–8832. PMLR, 2022. [Paper] [Video] [Code]