Eleven papers accepted for machine learning conference, ICML 2018
Posted: 22nd May 2018
Members of Oxford’s Department of Computer Science have co-authored 11 papers that have been accepted for this year's International Conference on Machine Learning (ICML) 2018.
This is a significant achievement as only 25% of all submitted papers were accepted (618 out of a total 2473) for this prestigious conference, which will be held in Stockholm on 10 -15 July 2018.
The accepted papers are the following (members of Oxford’s Department of Computer Science are asterixed):
- ‘TACO: Learning Task Decomposition via Temporal Alignment for Control’ - Kyriacos Shiarlis*, Markus Wulfmeier, Sasha Salter, Shimon Whiteson*, Ingmar Posner
- ‘Deep Variational Reinforcement Learning for POMDPs’ - Maximilian Igl*, Luisa Zintgraf*, Tuan Anh Le, Frank Wood, Shimon Whiteson*
- ‘QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning’ - Tabish Rashid*, Mikayel Samvelyan, Christian Schroeder de Witt*, Gregory Farquhar*, Jakob Foerster*, Shimon Whiteson*
- ‘Fourier Policy Gradients’ - Matthew Fellows*, Kamil Ciosek*, Shimon Whiteson*
- ‘DiCE: The Infinitely Differentiable Monte-Carlo Estimator’ - Jakob Foerster*, Greg Farquhar*, Maruan Al-Shedivat, Tim Rocktäschel*, Eric P. Xing, Shimon Whiteson*
- ‘Vprop: Variational Inference using RMSprop’ - Mohammad Emtiyaz Khan, Zuozhu Liu, Voot Tangkaratt, Yarin Gal*
- ‘Progress & Compress: A scalable framework for continual learning’ - Jonathan Schwarz, Jelena Luketina*, Wojciech M. Czarnecki, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell
- ‘The Mechanics of n-Player Differentiable Games’ – David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster*, Karl Tuyls, Thore Graepel
- ‘Tighter Variational Bounds are Not Necessarily Better’ - Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl*, Frank Wood, Yee Whye Teh
- ‘TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service' - Amartya Sanyal*, Matt Kusner, Adria Gascon, Varun Kanade*
- ‘Vadam: Fast and Scalable Variational Inference by Perturbing Adam' - Mohammad Emtiyaz Khan, Voot Tangkaratt, Didrik Nielsen, Wu Lin, Yarin Gal*, Zuozhu Liu, Akash Srivastava