I am a PhD researcher in Machine Learning at Imperial College London supervised by Mark van der Wilk. I am also a visiting student at the University of Oxford. Previously, I worked as a research scientist at Babylon Health. Interned at Amazon Research.

Research

I am generally interested in researching useful inductive biases for building more efficient and robust systems. I believe Causality and Bayesian ideas to be key for this. Currently, I have been working on developing flexible approaches to causal discovery using Bayesian model selection, with the aim of applying causal discovery to real world problems. Here I am particularly excited about using Neural processes to develop a foundation model approach to causal discovery. I also hope to use insights from this in improving robustness and generalisation of machine learning systems. Recently, I have also been interested in scaling theory for neural networks. Feel free to reach out if any of these topics interest you.

A non-exhaustive list of topics I am interested in:

• Causality: causal discovery, effect estimation, causal representation learning
• Model selection: Bayesian model selection, MDL
• Bayesian methods: Bayesian deep learning, Gaussian processes, probabilistic models, inference methods
• Generative models: Neural proceses, Diffusion, flow matching
• Deep learning: Local learning rules, generalisation, scaling theory, NTK, Tensor Programs
• Information theory: Kolmogorov complexity, information bottleneck

News

• Jan 2025: “A Meta-Learning Approach to Bayesian Causal Discovery” accepted at ICLR 2025.
• May - Nov 2024: Completed an internship at Amazon AGI Foundations working on scaling neural network architectures while preserving feature learning.