Seventeen Recent Papers from MLG

INTERNATIONAL CONFERENCE ON LEARNING REPRESENTATIONS, Vancouver. 2018

Yingzhen Li and Richard E. Turner.

Gradient Estimators for Implicit Models.

Alexander. G. de G. Matthews, Jiri Hron, Mark Rowland, Richard E. Turner, Zoubin Ghahramani.

Gaussian Process Behaviour in Wide Deep Neural Networks.

David Janz, J. van der Westhuizen , Brooks Paige, M. Kusner and José Miguel Hernández-Lobato

Learning a Generative Model for Validity in Complex Discrete Structures.

Cuong V. Nguyen, Yingzhen Li, Thang D. Bui, Richard E. Turner.

Variational Continual Learning.

V. Pong*, Shixiang Gu*, M. Dalal and S. Levine.

Temporal Difference Models: Model-Free Deep RL for Model-Based Control.

B. Eysenbach, Shixiang Gu, J. Ibarz and S. Levine.

Leave No Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning

AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, New Orleans. 2018

A. Vergari, Robert Peharz, N. Di Mauro, A. Molina, K. Kersting, and F. Esposito.

Sum-product autoencoding: Encoding and decoding representations using sum-product networks.

W. Dabney, Mark Rowland, M. G. Bellemare, R. Munos

Distributional Reinforcement Learning with Quantile Regression.

N. Grgic-Hlaca, M. Zafar, K. P. Gummadi and Adrian Weller.

Beyond Distributive Fairness in Algorithmic Decision Making: Feature Selection for Procedurally Fair Learning.

Y. Mukuta, Akisato Kimura, D. B Adrian, Zoubin Ghahramani,

Weakly supervised collective feature learning from curated media.

AAAI CONFERENCE ON ETHICS AND SOCIETY, New Orleans. 2018

M. Babaei, J. Kulshrestha, A. Chakraborty, F. Benevenuto, K. P. Gummadi and Adrian Weller.

Purple Feed: Identifying High Consensus News Posts on Social Media.

[Oral presentation].

INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, Lanzarote. 2018

Hong Ge, K. Xu, Zoubin Ghahramani

Turing: a language for composable probabilistic inference

Mark Rowland, M. G. Bellemare, W. Dabney, R. Munos, Y. W. Teh

An Analysis of Categorical Distributional Reinforcement Learning

S. Ahn, M. Chertkov, J. Shin and Adrian Weller.

Gauged mini-bucket elimination for approximate inference.

K. Choromanski, Mark Rowland, T. Sarlos, V. Sindhwani, Richard E. Turner, Adrian Weller.

The Geometry of Random Features.

JOURNAL OF MACHINE LEARNING RESEARCH. 2017

Thang D. Bui, Josiah Yan and Richard E. Turner

A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation.

THE WEB CONFERENCE, Lyon. 2018

N. Grgic-Hlaca, E. Redmiles, K. P. Gummadi and Adrian Weller.

Human perceptions of fairness in algorithmic decision making: A case study of criminal risk prediction.

*Denotes equal contribution