At the moment I'm working on quantifying and improving the robustness of Gaussian process regression to outliers in the training data. Generally, I am interested in developing methodology for probabalistic modelling and inference. I am particularly excited about working on tools which are useful in the fight against climate change.
If you would like to get in touch, feel free to send me an email!
- 2020 -
- PhD candidate in Computer Science UCL Supervised by François-Xavier Briol and Marc Deisenroth.
- 2019 - 2020
- Research Assistant in Bayesian Deep Learning University of Oxford Oxford Applied and Theoretical Machine Learning (OATML) group, supervised by Yarin Gal
- 2018 - 2019
- MSc in Computer Science University of Oxford Dissertation on "A comparison of uncertainty estimates for safe exploration in machine learning", supervised by Zac Kenton, Tim G. J. Rudner, Yarin Gal
- 2016 - 2018
- Software Engineer Google Encryption of Android backup data using a client-side key, released in Android 9
- 2013 - 2016
- BA in Computer Science University of Cambridge Dissertation on "Implementing and evaluating algebraic effect based code migration", supervised by Ohad Kammar
Research and code
- On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes arXiv code ICML 2021 poster
- Interlocking Backpropagation: Improving depthwise model-parallelism arXiv code
- Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties arXiv code AISTATS 2021 poster
- Uncertainty-Aware Counterfactual Explanations for Medical Diagnosis ML4H Workshop at NeurIPS 2020
- PyTorch library for constrained MPC, using the cross-entropy method code