Professor Yee Whye Teh

Professor of Statistical Machine Learning

Biographical Sketch

Prior to joining Oxford, I was a Lecturer then Reader of Computational Statistics and Machine Learning at the Gatsby Neuroscience Unit, UCL from 2007 to 2012. I obtained my PhD in Computer Science at the University of Toronto in 2003. This was followed by two years as a postdoctoral fellow at University of California, Berkeley, then as Lee Kuan Yew Postdoctoral Fellow at the National University of Singapore.

Research Interests

My research interests lie in the general areas of machine learning, Bayesian statistics and computational statistics. Although my group works on a variety of topics ranging from theoretical, through to methodological and applications, I am personally particularly interested in three (overlapping) themes: Bayesian nonparametrics and probabilistic learning, large scale machine learning, and deep learning.

These themes are motivated by the phenomenal growth in the quantity, diversity and heterogeneity of data now available. The analysis of such data is crucial to opening doors to new scientific frontiers and future economic growth. In the longer term, the development of general methods that can deal with such data are important testing grounds for artificial general intelligence systems.

Publications

Maddison, C., Paulin, D., Teh, Y. and Doucet, A. (2021) “Dual space preconditioning for gradient descent”, SIAM Journal on Optimization, 31(1), pp. 991–1016.

Ton, J.-F., Chan, L., Teh, Y. and Sejdinovic, D. (2021) “Noise contrastive meta-learning for conditional density estimation using kernel mean embeddings”, in. Journal of Machine Learning Research, pp. 1099–1107.

Brauner, J., Mindermann, S., Sharma, M., Johnston, D., Salvatier, J., Gavenčiak, T., Stephenson, A., Leech, G., Altman, G., Mikulik, V., Norman, A., Monrad, J., Besiroglu, T., Ge, H., Hartwick, M., Teh, Y., Chindelevitch, L., Gal, Y. and Kulveit, J. (2021) “Inferring the effectiveness of government interventions against COVID-19.”, Science (New York, N.Y.), 371(6531), p. eabd9338.

Hutchinson, M., Terenin, A., Borovitskiy, V., Takao, S., Teh, Y. and Deisenroth, M. (2021) “Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independant Projected Kernels”, in Advances in Neural Information Processing Systems, pp. 17160–17169.

Ton, J., Chan, L., Teh, Y. and Sejdinovic, D. (2021) “Noise Contrastive Meta-Learning for Conditional Density Estimation using Kernel Mean Embeddings”, in Proceedings of Machine Learning Research, pp. 1099–1107.

Hayou, S., Ton, J., Doucet, A. and Teh, Y. (2021) “ROBUST PRUNING AT INITIALIZATION”, in ICLR 2021 - 9th International Conference on Learning Representations.

Rudner, T., Lu, C., Osborne, M., Gal, Y. and Teh, Y. (2021) “On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations”, in Advances in Neural Information Processing Systems, pp. 28376–28389.

Schwarz, J., Jayakumar, S., Pascanu, R., Latham, P. and Teh, Y. (2021) “Powerpropagation: A sparsity inducing weight reparameterisation”, in Advances in Neural Information Processing Systems, pp. 28889–28903.

Chau, S., Ton, J., González, J., Teh, Y. and Sejdinovic, D. (2021) “BAYESIMP: Uncertainty Quantification for Causal Data Fusion”, in Advances in Neural Information Processing Systems, pp. 3466–3477.

Xu, J., Kim, H., Rainforth, T. and Teh, Y. (2021) “Group Equivariant Subsampling”, in Advances in Neural Information Processing Systems, pp. 5934–5946.

Contact Details

Email: yee.teh@stats.ox.ac.uk

Office: 1.16

Research Groups

Computational Statistics and Machine Learning

Statistical Theory and Methodology