Tim G. J. Rudner

PhD Candidate, Department of Computer Science, University of Oxford

  Oxford Applied & Theoretical Machine Learning Group (OATML)

  Oxford Computational Statistics & Machine Learning Group (OxCSML)

Wolfson Building, Parks Road, Oxford OX1 3QD, United Kingdom

tim.rudner [AT] cs.ox.ac.uk

About

I am a PhD Candidate in the Department of Computer Science at the University of Oxford, where I conduct research on probabilistic machine learning with Yarin Gal and Yee Whye Teh. My research interests span Bayesian deep learning, reinforcement learning, and variational inference. I am particularly interested in reinforcement learning as probabilistic inference, uncertainty quantification in deep learning, and probabilistic meta-learning. I am also a Rhodes Scholar.

Bio

I obtained an undergraduate degree in mathematics and economics from Yale University, where I received the Charles E. Clark Memorial Award for Academic Excellence and was fortunate to be advised by Sekhar Tatikonda. Subsequently, I earned a master's degree in statistics from the University of Oxford, where I was supervised by Dino Sejdinovic. Prior to starting my PhD, I conducted research on approximate inference in Deep Gaussian Process models, game theoretic equilibria in digital goods markets, and drivers of financial crises. I am a member of the Oxford Center for Doctoral Training in Autonomous Intelligent Machines & Systems (AIMS) and a Fellow of the German National Academic Foundation.

News

Publications

Mult3Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery

Tim G. J. Rudner, Marc Rußwurm, Jakub Fil, Ramona Pelich, Benjamin Bischke, Veronika Kopackova, Piotr Bilinski

AAAI Conference on Artificial Intelligence. 2019.

NeurIPS Workshop on AI for Social Good. 2018.

   arXiv      Code   Bibtex  Media 

The StarCraft Multi-Agent Challenge

Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob Foerster, Shimon Whiteson

AAMAS International Conference on Autonomous Agents and Multiagent Systems. 2019.

   arXiv      Code   Bibtex

On the Connection between Neural Processes and Gaussian Processes with Deep Kernels

Tim G. J. Rudner, Vincent Fortuin, Yee Whye Teh, Yarin Gal

NeurIPS Workshop on Bayesian Deep Learning. 2018.

  Paper   Bibtex

VIREL: A Variational Inference Framework for Reinforcement Learning

Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner, Shimon Whiteson

NeurIPS Workshop on Probabilistic Reinforcement Learning and Structured Control. 2018.

   arXiv    Bibtex

Inter-domain Deep Gaussian Processes

Tim G. J. Rudner and Dino Sejdinovic

NIPS Workshop on Bayesian Deep Learning. 2017.

  Paper   Bibtex

Teaching

A selection of classes I've TA'ed for in the past: