I am a final year PhD student at UCL in the Centre for Artificial Intelligence, supervised by François-Xavier Briol and Marc Deisenroth.

I'm currently interested in making large machine learning models more efficient, via both modelling and systems approaches, and writing nice software along the way. I am also excited about working on tools for climate change mitigation and adaptation.

Bio

2020 - 2025

PhD candidate in Computer Science UCL Supervised by François-Xavier Briol and Marc Deisenroth Internships: Graphcore, Seqana (measuring soil carbon content using satellite imagery)

2019 - 2020

Research Assistant in Bayesian Deep Learning University of Oxford OATML group, supervised by Yarin Gal

2018 - 2019

MSc in Computer Science University of Oxford

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

Research and code

• Scalable Data Assimilation with Message Passing Oscar Key*, So Takao*, Daniel Giles*, Marc Peter Deisenroth arXiv code Climate Informatics 2024 oral
• No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models Jean Kaddour*, Oscar Key*, Piotr Nawrot, Pasquale Minervini, Matt J. Kusner arXiv code NeurIPS 2023 poster
• Interlocking Backpropagation: Improving depthwise model-parallelism Aidan N. Gomez*, Oscar Key*, Kuba Perlin, Stephen Gou, Nick Frosst, Jeff Dean, Yarin Gal arXiv code JMLR
• Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference Ayush Bharti, Masha Naslidnyk, Oscar Key, Samuel Kaski, François-Xavier Briol arXiv code ICML 2023 poster
• Towards Healing the Blindness of Score Matching Mingtian Zhang, Oscar Key, Peter Hayes, David Barber, Brooks Paige, François-Xavier Briol arXiv Workshop on Score-Based Methods NeurIPS 2022
• Composite Goodness-of-fit Tests with Kernels Oscar Key*, Arthur Gretton, François-Xavier Briol, Tamara Fernandez* arXiv code talk Your Model is Wrong Workshop NeurIPS 2021
• On Feature Collapse and Deep Kernel Learning for Single Forward Pass Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal arXiv code Bayesian Deep Learning Workshop at NeurIPS 2021
• On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes Tim G. J. Rudner*, Oscar Key*, Yarin Gal, Tom Rainforth arXiv code ICML 2021 poster
• Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties Lisa Schut*, Oscar Key*, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal arXiv code AISTATS 2021 poster
• PyTorch library for constrained MPC, using the cross-entropy method code