10 papers with MLG authors will appear at NeurIPS 2019 in Vancouver, Canada.

James Requeima, Jonathan Gordon, John Bronskill, Sebastian Nowozin, Richard E. Turner
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes (spotlight)
Paper

Wenbo Gong, Sebastian Tschiatschek, Richard E. Turner, Sebastian Nowozin, José Miguel Hernández-Lobato, Cheng Zhang
Icebreaker: Efficient Information Acquisition with Active Learning.
Paper

Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan
Practical Deep Learning with Bayesian Principles
Paper

Yunfei Teng, Wenbo Gao, Francois Chalus, Anna Choromanska, Donald Goldfarb, Adrian Weller
Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models.
Paper

Robert Pinsler, Jonathan Gordon, Eric Nalisnick, José Miguel Hernández-Lobato
Bayesian Batch Active Learning as Sparse Subset Approximation
Paper

Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani
Bayesian Learning of Sum-Product Networks
Paper

David Janz, Jiri Hron, Przemysław Mazur, Katja Hofmann, José Miguel Hernández-Lobato, Sebastian Tschiatschek
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
Paper

John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato
A Model to Search for Synthesizable Molecules
Paper

Paul Rubenstein, Olivier Bousquet, Josip Djolonga, Carlos Riquelme, Ilya Tolstikhin
Practical and Consistent Estimation of f-Divergences
Paper

Laurence Aitchison
Tensor Monte Carlo: Particle Methods for the GPU era
Paper

Congratulations to our PhD student David R. Burt, Prof. Carl E. Rasmussen and our PhD alumnus Mark van der Wilk (now at PROWLER.io) for receiving a Best Paper Award at ICML 2019 in Long Beach, CA, USA, for their paper Rates of Convergence for Sparse Variational Gaussian Process Regression (Paper)!

12 papers with MLG authors appeared at ICML 2019 in Long Beach, CA, USA.

David R. Burt, Carl E. Rasmussen and Mark van der Wilk
Rates of Convergence for Sparse Variational Gaussian Process Regression (Best Paper Award)
Paper

Francisco J. R. Ruiz and Michalis K. Titsias
A Contrastive Divergence for Combining Variational Inference and MCMC
Paper

Tameem Adel and Adrian Weller
TibGM: A Transferable and Information-Based Graphical Model Approach for Reinforcement Learning
Paper

Yingzhen Li, John Bradshaw and Yash Sharma
Are Generative Classifiers More Robust to Adversarial Attacks?
Paper

Alessandro Davide Ialongo, Mark van der Wilk, James Hensman and Carl E. Rasmussen
Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models
Paper

Chao Ma, Sebastian Tschiatschek, Konstantina Palla, José Miguel Hernández- Lobato, Sebastian Nowozin and Cheng Zhang
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Paper

Chao Ma, Yingzhen Li and José Miguel Hernández-Lobato
Variational Implicit Processes
Paper

Ping Liang Tan and Robert Peharz
Hierarchical Decompositional Mixtures of Variational Autoencoders
Paper

Krzystof Choromanski, Mark Rowland, Wenyu Chen and Adrian Weller
Unifying Orthogonal Monte Carlo Methods
Paper

Eric Nalisnick, Akihito Matsukawa, Yee Whye Teh, Dilan Gorur and Balaji Lakshminarayanan
Hybrid Models with Deep and Invertible Features
Paper

Eric Nalisnick, José Miguel Hernández-Lobato and Padhraic Smyth
Dropout as a Structured Shrinkage Prior
Paper

Karl Stelzner, Robert Peharz and Kristian Kersting
Faster Attend-Infer-Repeat with Tractable Probabilistic Models
Paper