Yee Whye Teh
Also known as Yee Teh
Yee Whye Teh is a professor of statistical machine learning at Oxford whose research spans Bayesian models, deep belief networks and generative models. His academic path runs from a Toronto PhD through postdoctoral work at Berkeley and Singapore to UCL's Gatsby Neuroscience Unit. With collaborators, he develops the hierarchical Dirichlet process for sharing mixture components across groups and publishes a fast learning algorithm for deep belief networks. At ICML, he serves as a 2017 program chair; by 2022, he is a Faculty Fellow at the Alan Turing Institute for Data Science and a Research Scientist at DeepMind. Two papers he coauthors receive ICML's 2021 Test of Time award and NeurIPS's 2022 Outstanding Paper award; ELLIS lists him as Program Director and Fellow.
- Now at
- University of Oxford and ELLIS
- Works
- 316
Publication numbers from OpenAlex, as of 14 October 2026. Citations and h-index are hidden because this OpenAlex record may be incomplete or mix in other authors.
Timeline
-
2003–2012
From Toronto to UCL
At the University of Toronto, he completes a PhD in computer science in 2003, then does postdoctoral work at the University of California, Berkeley and the National University of Singapore. At UCL's Gatsby Neuroscience Unit, he serves as Lecturer and then Reader in Computational Statistics and Machine Learning from 2007 to 2012.
-
2004
Sharing clusters across groups
With Michael I. Jordan, Matthew J. Beal and David M. Blei, he coauthors the 2004 paper Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes. The model lets groups share mixture components.
-
2006
Training deep belief networks
Together with Geoffrey Hinton and Simon Osindero, he publishes a fast learning algorithm for deep belief networks.
-
2017
Co-chairing ICML
Alongside Doina Precup, he serves as an ICML 2017 Program Chair.
-
2021–2022
Papers and research roles
Bayesian Learning via Stochastic Gradient Langevin Dynamics, a paper he coauthors with Max Welling, receives ICML's 2021 Test of Time award. Riemannian Score-Based Generative Modelling, his paper with five other authors, receives NeurIPS's 2022 Outstanding Paper award. By 2022, he is a Faculty Fellow at the Alan Turing Institute for Data Science and a Research Scientist at DeepMind.
-
As of October 2026
Oxford and ELLIS
Oxford lists him as Professor of Statistical Machine Learning. ELLIS lists him as Program Director and Fellow.
Sources and credits
Photo: stats.ox.ac.uk; Yee Whye Teh; creator not stated. License: Not stated by source. Source: stats.ox.ac.uk. Cropped to a square and resized. Ask us to remove or replace this photo.
- Professor Yee Whye Teh | Department of Statistics - University of Oxford
- Yee Whye Teh - Oxford Sparks
- Yee Whye Teh
- OxCSML : People : Yee Whye Teh
- iCML 2017 Committees
- ICML Test Of Time Bayesian Learning via Stochastic Gradient Langevin Dynamics
- NeurIPS 2022 Awards
- Yee Whye Teh | European Laboratory for Learning and Intelligent Systems