I design and analyse bandit and reinforcement learning algorithms, and develop the theoretical foundations of statistics and machine learning, particularly in the context of sequential decision-making (e.g. medical trials where continuation decisions are made adaptively).

Before this position, I worked with Csaba Szepesvári at the University of Alberta. I completed my PhD at Cambridge, supervised by José Miguel Hernández-Lobato and Zoubin Ghahramani. My career began at Oxford, where I read Engineering, Economics, and Management.

If you're considering a PhD/DPhil in machine learning theory at Oxford, feel free to email me.

Selected works

Abeille, Marc, David Janz, and Ciara Pike-Burke. "When and why randomised exploration works (in linear bandits)." Outstanding Paper Award, International Conference on Algorithmic Learning Theory (2025).

Janz, David, et al. "Exploration via linearly perturbed loss minimisation." Oral Presentation, International Conference on Artificial Intelligence and Statistics (2024).

Lin, Jihao Andreas, et al. "Sampling from Gaussian process posteriors using stochastic gradient descent." Oral Presentation, International Conference on Neural Information Processing Systems (2023)