Skip to main content

Eighteen Oxford Computer Science papers at NeurIPS-2019

Posted:

Members of the Department of Computer Science have co-authored 18 papers accepted for the forthcoming NeurIPS conference to be held in Vancouver, Canada, in December 2019. NeurIPS is the premierinternational forum for research on machine learning: this year 6743 papers were submitted, of which only 1428 were accepted (an acceptance rate of just 21%).
For more information on NeurIPs-2019 see:
Oxford computer science co-authored papers are as follows:
A Geometric Perspective on Optimal Representations for Reinforcement
Learning
M. Bellemare, W. Dabney, R. Dadashi-Tazehozi, A. Ali Taiga, P. Samuel
Castro, N. Le Roux. D. Schuurmans, T. Lattimore, and C. Lyle.
Variational Bayesian Optimal Experimental Design
A. Foster, M. Jankowiak, E. Bingham, P. Horsfall, Y. Whye Teh, Tom
Rainforth, and N. Goodman.
On the Benefits of Disentangled Representations
F. Locatello, G. Abbati, T. Rainforth, S. Bauer, Bernhard Schölkopf,
and O. Bachem.
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian
Active Learning
A. Kirsch, J. van Amersfoort, and Y. Gal.
Learning Object Bounding Boxes for 3D Instance Segmentation on Point
Clouds
B. Yang, J. Wang, R. Clark, Q. Hu, S. Wang, A.
Markham, and N. Trigoni.
Generalization in Reinforcement Learning with Selective Noise
Injection and Information Bottleneck
M. Igl, K. Ciosek, Y. Li, S. Tschiatschek, C. Zhang, S. Devlin, and
K. Hofmann.
Generalized Off-Policy Actor-Critic
S. Zhang, W. Boehmer, S. Whiteson
DAC: The Double Actor-Critic Architecture for Learning Options
S. Zhang, and S. Whiteson
Fast Efficient Hyperparameter Tuning for Policy Gradient Methods
S. Paul, V. Kurin, S. Whiteson
VIREL: A Variational Inference Framework for Reinforcement Learning
M. Fellows, A. Mahajan, T. G. J. Rudner, and S. Whiteson
MAVEN: Multi-Agent Variational Exploration
A. Mahajan, T. Rashid, M. Samvelyan, and S. Whiteson
Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function
Gradient Estimators for Reinforcement Learning
G. Farquhar, S. Whiteson, and J. Foerster
Multi-Agent Common Knowledge Reinforcement Learning.  * = equal
contribution
C. Schroeder de Witt*, J. Foerster*, G. Farquhar,
P. Torr, W. Boehmer, and S. Whiteson
Controllable Text-to-Image Generation
B. Li, X. Qi, T. Lukasiewicz, and P. H. S. Torr.
Implicit Regularization for Optimal Sparse Recovery
T. Vaskevicius, V. Kanade, and P. Rebeschini.
Decentralized Cooperative Stochastic Bandits
D. Martínez-Rubio, V. Kanade, and P. Rebeschini.
On the Hardness of Robust Classification
P. Gourdeau, V. Kanade, M. Kwiatkowska, and J. Worrell.
Manipulating a Learning Defender and Ways to Counteract
J. Gan, B. An, G. Qingyu, L. Tran-Tranh, and M. Wooldridge.