I am a PhD researcher in Machine Learning at Imperial College London supervised by Mark van der Wilk. Previously, worked as a research scientist at Babylon Health.
I am generally interested in researching how to build robust systems that can generalise beyond the training data. A non-exhaustive list of topics I am interested in:
- Causality: causal discovery, effect estimation, representation learning
- Model selection: Bayesian model selection, MDL
- Bayesian methods: Bayesian deep learning, Gaussian processes, probabilistic models, inference methods
- Deep learning: Local learning rules, generalisation
- Information theory: Kolmogorov complexity, information bottleneck