I am a PhD candidate in the Computational and Biological Learning lab at the University of Cambridge, supervised by Dr Richard E Turner and advised by Prof Carl Rasmussen. I am interested in designing algorithms for large-scale machine learning systems that learn sequentially without revisiting past data, are private over user data, and are uncertainty-aware.
I use probabilistic methods, and have focussed on approximate Bayesian inference techniques, usually variational inference. My research scales these techniques to large Bayesian neural network models, and applies these to the continual learning (/lifelong learning) and federated learning problems.
List of publications.
|Jan 2021||Paper at ICLR 2021, Generalized Variational Continual Learning.|
Oral presentation at NeurIPS 2020, Continual Deep Learning by Functional Regularisation of Memorable Past (top 1% of submissions, 105/10K).
Paper at NeurIPS 2020, Efficient Low Rank Gaussian Variational Inference for Neural Networks.
|Jul 2020||Two orals at LifeLongML Workshop (ICML 2020), Combining Variational Continual Learning with FiLM Layers and Continual Deep Learning by Functional Regularisation of Memorable Past.|
|Jun 2020||I have been awarded a Microsoft Research EMEA PhD Award.|
|Dec 2019||Paper at NeurIPS 2019, Practical Deep Learning with Bayesian Principles.|