22 OATML Conference and Workshop papers at NeurIPS 2020

Muhammed Razzak, Panagiotis Tigas, Angelos Filos, Atılım Güneş Baydin, Andrew Jesson, Andreas Kirsch, Clare Lyle, Freddie Kalaitzis, Jan Brauner, Jishnu Mukhoti, Lewis Smith, Lisa Schut, Mizu Nishikawa-Toomey, Oscar Key, Binxin (Robin) Ru, Sebastian Farquhar, Sören Mindermann, Tim G. J. Rudner, Yarin Gal, 04 Dec 2020

OATML group members and collaborators are proud to be presenting 22 papers at NeurIPS 2020, including 7 papers at the main conference and 15 papers at various workshops. These papers range from theoretical work, including a paper analysing Bayesian Neural Networks, to more applied work, including a timely paper assessing the robustness of models estimating the effects of nonpharmaceutical internventions against COVID-19. Group members are also co-organising various events around NeurIPS, including workshops, the NeurIPS Meet-Up on Bayesian Deep Learning and socials. Lisa Schut will be co-facilitating the Applying to and Navigating PhDs session at the Women in Machine Learning workshop.

Conference Papers

How Robust are the Estimated Effects of Nonpharmaceutical Interventions against COVID-19?
Mrinank Sharma, Sören Mindermann, Jan Brauner, Gavin Leech, Anna Stephenson, Tomáš Gavenčiak, Jan Kulveit, Yee Whye Teh, Leonid Chindelevitch, Yarin Gal
Spotlight Presentation: Orals & Spotlights: COVID/Applications/Composition at 16:30 – 16:40 GMT on Wednesday, 9 December 2020
Poster: Poster Session 3 at 17:00 – 19:00 GMT on Wednesday, 9 December 2020

Identifying Causal-Effect Inference Failure with Uncertainty-Aware Models
Andrew Jesson, Sören Mindermann, Uri Shalit, Yarin Gal
Poster: Poster Session 3 at 17:00 – 19:00 GMT on Wednesday, 9 December 2020

Neural Architecture Generator Optimization
Binxin Ru, Pedro M Esperança, Fabio Maria Carlucci
Poster: Poster Session 3 at 17:00 – 19:00 GMT on Wednesday, 9 December 2020

Black-Box Optimization with Local Generative Surrogates
Sergey Shirobokov, Vladislav Belavin, Michael Kagan, Andrei Ustyuzhanin, Atılım Güneş Baydin
Poster: Poster Session 3 at 17:00 – 19:00 GMT on Wednesday, 9 December 2020

A Bayesian Perspective on Training Speed and Model Selection
Clare Lyle, Lisa Schut, Binxin Ru, Yarin Gal, Mark van der Wilk
Poster: Poster Session 5 at 17:00 – 19:00 GMT on Thursday, 10 December 2020

Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
Sebastian Farquhar, Lewis Smith, Yarin Gal
Poster: Poster Session 5 at 17:00 – 19:00 GMT on Thursday, 10 December 2020

Calibrating Deep Neural Networks using Focal Loss
Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip Torr, Puneet Dokania
Poster: Poster Session 5 at 17:00 – 19:00 GMT on Thursday, 10 December 2020

Workshops Papers

Uncertainty-Aware Counterfactual Explanations for Medical Diagnosis
Lisa Schut, Oscar Key, Rory McGrath, Luca Costabello, Bogdan Sacaleanu, Medb Corcoran, Yarin Gal
Workshop: Machine Learning for Health (ML4H): Advancing Healthcare for All
Date: 16:30-17:30 GMT on Friday, 11 December 2020

Real2sim: Automatic Generation of Open Street Map Towns For Autonomous Driving Benchmarks
Avishek Mandal, Panagiotis Tigas, Yarin Gal
Workshop: Machine Learning for Autonomous Driving
Date: 16:55 GMT on Friday, 11 December to 01:00 on GMT Saturday, 12 December 2020

Spatial Assembly:Generative Architecture With Reinforcement Learning, Self Play and Tree Search
Panagiotis Tigas, Tyson Hosmer
Workshop: Machine Learning for Creativity and Design
Date: 13:15 – 23:00 GMT on Saturday, 12 December 2020

Beliefs and Level-k Reasoning in Traffic
Eugene Vinitsky, Angelos Filos, Nathan Lichtle, Kevin Lin, Nicholas Liu, Alexandre Bayen, Anca Dragan, Rowan McAllister and Jakob Foerster
Workshop: Talking to Strangers: Zero-Shot Emergent Communication
Date: 15:00 – 22:10 GMT on Saturday, 12 December 2020

Outcome-Driven Reinforcement Learning via Variational Inference
Tim G. J. Rudner, Vitchyr H. Pong, Rowan McAllister, Yarin Gal, Sergey Levine
Workshop: Deep Reinforcement Learning
Date: 16:30 GMT on Friday, 11 December 2020 to 03:00 GMT on Saturday, Dec 12th

Global Earth Magnetic Field Modeling and Forecasting with Spherical Harmonics Decomposition
Panagiotis Tigas, Téo Bloch, Vishal Upendran, Bashi Ferdoushi, Yarin Gal, Siddha Ganju, Ryan M. McGranaghan, Mark C. M. Cheung, Asti Bhatt
Workshop: Machine Learning and the Physical Sciences
Date: 15:00 – 23:15 GMT on Friday, 11 December 2020

Semi-supervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
Mizu Nishikawa-Toomey, Lewis Smith, Yarin Gal
Workshop: Machine Learning and the Physical Sciences
Date: 15:00 – 23:15 GMT on Friday, 11 December 2020

Dynamic Hydrology Maps from Satellite-LiDAR Fusion
Dolores Garcia, Gonzalo Mateo-Garcia, Hannes Bernhardt, Ron Hagensieker, Ignacio G. Lopez Francos, Jonathan Stock, Guy Schumann, Kevin Dobbs, Freddie Kalaitzis
Workshop: AI for Earth Sciences
Date: Spotlight talk at 19:55 GMT on Saturday, 12 December 2020

Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery
Issam Laradji, Pau Rodriguez, Freddie Kalaitzis, David Vazquez, Ross Young, Ed Davey, Alexandre Lacoste
Workshop: Tackling Climate Change with Machine Learning
Date: Friday, 11 December 2020

RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale
Catherine Tong, Christian Schroeder de Witt, Valentina Zantedeschi, Daniele De Martini, Freddie Kalaitzis, Matthew Chantry, Duncan Watson-Parris, Piotr Biliński
Workshop: Tackling Climate Change with Machine Learning
Date: 13:00-14:00 and 16:00-17:00 GMT on Friday, 11 December 2020
Workshop: AI for Earth Sciences
Date: Spotlight talk at 17:30 GMT on Saturday, 12 December 2020

Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery
Valentina Zantedeschi, Daniele De Martini, Catherine Tong, Christian Schroeder de Witt, Freddie Kalaitzis, Piotr Biliński, Matthew Chantry, Duncan Watson-Parris
Workshop: Tackling Climate Change with Machine Learning
Date: 13:00-14:00 and 16:00-17:00 GMT on Friday, 11 December 2020
Workshop: AI for Earth Sciences
Date: Lightning talk at 22:50 GMT on Saturday, 12 December 2020

Spacecraft Collision Risk Assessment with Probabilistic Programming
Acciarini, Giacomo, Francesco Pinto, Sascha Metz, Sarah Boufelja, Sylvester Kaczmarek, Klaus Merz, José A. Martinez-Heras, Francesca Letizia, Christopher Bridges, Atılım Güneş Baydin
Workshop: Machine Learning and the Physical Sciences
Date: 15:00 – 23:15 GMT on Friday, 11 December 2020

Towards Automated Satellite Conjunction Management with Bayesian Deep Learning
Pinto, Francesco, Giacomo Acciarini, Sascha Metz, Sarah Boufelja, Sylvester Kaczmarek, Klaus Merz, José A. Martinez-Heras, Francesca Letizia, Christopher Bridges, Atılım Güneş Baydin
Workshop: AI for Earth Sciences
Date: Saturday, 12 December 2020

Workshop and Meet-Ups

NeurIPS Europe meetup on Bayesian Deep Learning
Yarin Gal, Sebastian Farquhar, Yingzhen Li, Andrew G. Wilson, Christos Louizos, Eric Nalisnick, Zoubin Ghahramani, Kevin Murphy, Max Welling
Date: 11:00 - 18:00 GMT on Thursday, December 10 2020

Machine Learning and the Physical Sciences Workshop
Atılım Güneş Baydin, Juan Felipe Carrasquilla, Adji Bousso Dieng, Karthik Kashinath, Gilles Louppe, Brian Nord, Michela Paganini, Savannah Thais, Anima Anandkumar, Kyle Cranmer, Shirley Ho (Princeton University), Prabhat, Lenka Zdeborova
Date: 15:00 – 23:15 GMT on Friday, 11 December 2020

Talking to Strangers: Zero-Shot Emergent Communication
Marie Ossenkopf, Angelos Filos, Abhinav Gupta, Michael Noukhovitch, Angeliki Lazaridou, Jakob Foerster, Kalesha Bullard, Rahma Chaabouni, Eugene Kharitonov, Roberto Dessì
Date: 15:00 – 22:10 GMT on Saturday, 12 December 2020

WIML Social: Applying to and Navigating PhDs
Lisa Schut, Limor Gultchin, Luisa Zintgraf
Date: 9:40 - 10:40 GMT on Wednesday, 9 December 2020

SpaceML Social: An applied AI developer community for space science and exploration
Sara Jennings, Freddie Kalaitzis, James Parr
Date: 20:00 - 22:00 GMT on Thursday, 10 December 2020


More blog posts here: OATML Blog


Are you looking to do a PhD in machine learning? Did you do a PhD in another field and want to do a postdoc in machine learning? Would you like to visit the group?

How to apply


Contact

We are located at
Department of Computer Science, University of Oxford
Wolfson Building
Parks Road
OXFORD
OX1 3QD
UK
Twitter: @OATML_Oxford
Github: OATML
Email: oatml@cs.ox.ac.uk