Y
Yee Whye Teh
Researcher at University of Oxford
Publications - 351
Citations - 42930
Yee Whye Teh is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Inference. The author has an hindex of 68, co-authored 326 publications receiving 36155 citations. Previous affiliations of Yee Whye Teh include University of Toronto & University College London.
Papers
More filters
Posted Content
Conditional Neural Processes
Marta Garnelo,Dan Rosenbaum,Chris J. Maddison,Tiago Ramalho,David Saxton,Murray Shanahan,Yee Whye Teh,Danilo Jimenez Rezende,S. M. Ali Eslami +8 more
TL;DR: Conditional Neural Processes are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks and trained via gradient descent, yet scale to complex functions and large datasets.
Proceedings Article
Actor-Critic Reinforcement Learning with Energy-Based Policies
TL;DR: This work introduces the first sound and e"cient algorithm for training energy-based policies, based on an actorcritic architecture, that is computationally e-cient, converges close to a local optimum, and outperforms Sallans and Hinton (2004) in several high dimensional domains.
Proceedings Article
Spatial Normalized Gamma Processes
Vinayak Rao,Yee Whye Teh +1 more
TL;DR: In this paper, a simple and general framework is proposed to construct dependent Dirichlet processes by marginalizing and normalizing a single gamma process over an extended space, and the result is a set of DPs, each associated with a point in a space such that neighbouring DPs are more dependent.
Posted Content
Meta-learning of Sequential Strategies.
Pedro A. Ortega,Jane X. Wang,Mark Rowland,Tim Genewein,Zeb Kurth-Nelson,Razvan Pascanu,Nicolas Heess,Joel Veness,Alexander Pritzel,Pablo Sprechmann,Siddhant M. Jayakumar,Thomas M McGrath,Kevin J. Miller,Mohammad Gheshlaghi Azar,Ian Osband,Neil C. Rabinowitz,András György,Silvia Chiappa,Simon Osindero,Yee Whye Teh,Hado van Hasselt,Nando de Freitas,Matthew Botvinick,Shane Legg +23 more
TL;DR: This report recast memory-based meta-learning within a Bayesian framework, showing that the meta-learned strategies are near-optimal because they amortize Bayes-filtered data, where the adaptation is implemented in the memory dynamics as a state-machine of sufficient statistics.
Proceedings Article
The Unified Propagation and Scaling Algorithm
Yee Whye Teh,Max Welling +1 more
TL;DR: It is shown that a restricted class of constrained minimum divergence problems, named generalized inference problems, can be solved by approximating the KL divergence with a Bethe free energy.