9 ICML 2018 Accepted Papers

9 papers co-authored by the OxCSML group members have been accepted to the main program of ICML 2018:

• The Weighted Kendall and High-order Kernels for Permutations. Yunlong Jiao and Jean-Philippe Vert.

• TensOrMachine: Probabilistic Boolean Tensor Decomposition. Tammo Rukat, Chris C. Holmes, Christopher Yau.

• Disentangling by Factorising Hyunjik Kim, Andriy Mnih.

• Structured Variationally Auto-encoded Optimization. Xiaoyu Lu, Javier González, Zhenwen Dai, Neil Lawrence.

• On Nesting Monte Carlo Estimators. Tom Rainforth, Rob Cornish, Hongseok Yang, Andrew Warrington, Frank Wood.

• Tighter Variational Bounds are Not Necessarily Better. Tom Rainforth, Adam Kosiorek, Tuan Anh Le, Chris J. Maddison, Maximilian Igl, Frank Wood, Yee Whye Teh.

• Progress & Compress: A scalable framework for continual learning. Jonathan Schwarz, Wojciech Czarnecki, Jelena Luketina, Agnieszka Grabska-Barwinska, Yee Whye Teh, Razvan Pascanu, Raia Hadsell.

• Mix & Match - Agent Curricula for Reinforcement Learning. Wojciech Czarnecki, Siddhant Jayakumar, Max Jaderberg, Leonard Hasenclever, Yee Whye Teh, Nicolas Heess, Simon Osindero, Razvan Pascanu.

• Conditional Neural Processes. Marta Garnelo, Dan Rosenbaum, Chris Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende (DeepMind), S. M. Ali Eslami.