8 ICML 2020 Accepted Papers!

8 papers co-authored by the OxCSML group members have been accepted to the main program of ICML 2020

• Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
  Yuan Zhou (University of Oxford) Hongseok Yang (KAIST) Yee Whye Teh (University of Oxford) Tom Rainforth (University of Oxford)

• Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
  Rob Cornish (University of Oxford); Anthony Caterini (University of Oxford); George Deligiannidis (University of Oxford); Arnaud Doucet (University of Oxford)

• Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise
  Umut Simsekli (Institut Polytechnique de Paris / University of Oxford); Lingjiong Zhu (FSU); Yee Whye Teh (University of Oxford and DeepMind); Mert Gurbuzbalaban (Rutgers University)

• MetaFun: Meta-Learning with Iterative Functional Updates Jin Xu (University of Oxford); Jean-Francois Ton(University of Oxford); Hyunjik Kim (Google DeepMind); Adam R. Kosiorek (University of Oxford); Yee Whye Teh (University of Oxford)

• Decentralised Learning with Random Features and Distributed Gradient Descent Dominic Richards (University of Oxford); Patrick Rebeschini (University of Oxford); Lorenzo Rosasco (unige, mit, iit)

• Equivariant Neural Rendering
  Emilien Dupont (Oxford), Miguel Angel Bautista (Apple), Alex Colburn (Apple), Aditya Sankar (Apple), Josh Susskind (Apple), Qi Shan (Apple)

• Inter-domain Deep Gaussian Processes
  Tim G. J. Rudner (University of Oxford), Dino Sejdinovic (University of Oxford), Yarin Gal (University of Oxford)

• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
  Joost van Amersfoort (University of Oxford), Lewis Smith (University of Oxford), Yee Whye Teh (University of Oxford), Yarin Gal (University of Oxford)