University of Oxford, Department of Statistics Pride logo
Professor Tom Rainforth
Associate Professor of Statistical Machine Learning

Biographical sketch

I am an Associate Professor of Statistical Machine Learning, leader of the RainML Research Lab (rainml.uk), Tutorial Fellow at Mansfield College, and Principal Investigator of the ERC Starting Grant Data-Driven Algorithms for Data Acquisition (Mar 2024 - Feb 2029, funded by the UKRI Horizon Guarantee Scheme).  Though I only started my current Associate Professor role in September 2024, I have been a member of the Department since 2017, first as a postdoc working with Yee Whye Teh (Sep 2017 - Aug 2019), then as an associate member as part of a Junior Research Fellow in Computer Science at Christ Church College (Sep 2019 - Dec 2019), then as a Florence Nightingale Bicentennial Fellow and Tutor in Statistics and Probability (Jan 2020 - Feb 2024), and finally a Senior Research Fellow supported by my own ERC grant (Mar 2024 - Aug 2024). I originally studied Mechanical Engineering (MEng) at the University of Cambridge, while I did my D.Phil in Oxford under the supervision of Frank Wood and Michael Osborne, focusing mostly on probabilistic programming and Monte Carlo methods.  I also had a stint working in the Ferrari Formula 1 team in between the two.

Personal website: https://www.robots.ox.ac.uk/~twgr/

Research Interests

My research covers a wide range of topics in and around optimal experimental design and probabilistic machine learning, with areas of particular interest including: 

  • Bayesian experimental design
  • Active learning
  • Probabilistic machine learning
  • Uncertainty quantification
  • Large language models

Please see my Google Scholar page for an up-to-date list of publications.

Publications

Ivanova, D. et al. (2023) “CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design”, in Proceedings of Machine Learning Research, pp. 14445–14464.
Xu, J. et al. (2023) “Deep Stochastic Processes via Functional Markov Transition Operators”, in Advances in Neural Information Processing Systems.
Smith, F. et al. (2023) “Prediction-Oriented Bayesian Active Learning”, in Proceedings of Machine Learning Research, pp. 7331–7348.
Sharma, M. et al. (2023) “Do Bayesian Neural Networks Need To Be Fully Stochastic?”, in Proceedings of Machine Learning Research, pp. 7694–7722.
Miao, N. et al. (2023) “Learning Instance-Specific Augmentations by Capturing Local Invariances”, in Proceedings of Machine Learning Research, pp. 24720–24736.
Campbell, A. et al. (2022) “Online variational filtering and parameter learning”, in Advances in Neural Information Processing Systems 34 (NeurIPS 2021). Curran Associates, pp. 18633–18645.
Campbell, A. et al. (2022) “A Continuous Time Framework for Discrete Denoising Models”, arXiv.
Naderiparizi, S. et al. (2022) “Amortized rejection sampling in universal probabilistic programming”, in Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022). Journal of Machine Learning Research, pp. 8392–8412.
Joy, T. et al. (2022) “Learning multimodal VAEs through mutual supervision”, in International Conference on Learning Representations. OpenReview.
Reichelt, T., Ong, L. and Rainforth, T. (2022) “Rethinking Variational Inference for Probabilistic Programs with Stochastic Support”, in Advances in Neural Information Processing Systems.

Contact Details

Email: rainforth@stats.ox.ac.uk

Office: 1.21

Pronouns: He/Him

Postdocs

Emily Alger
Freddie Bickford Smith
Gavin Kerrigan
Sahel Iqbal

Graduate Students

Adhi Saravanan
Alex Forster
Angus Phillips
Benjamin Chang
Deepro Choudhury
Guneet Singh Dhillon
Kianoosh Ashouritaklimi
Ole Jorgensen
Marcel Hedman
Rik Knowles
Tom Rossa
Zhuoyue Huang