OATML at ICML 2022

Sören Mindermann, Jan Brauner, Muhammed Razzak, Andreas Kirsch, Aidan Gomez, Sebastian Farquhar, Pascal Notin, Tim G. J. Rudner, Freddie Bickford Smith, Neil Band, Panagiotis Tigas, Andrew Jesson, Lars Holdijk, Joost van Amersfoort, Kelsey Doerksen, Jannik Kossen, Yarin Gal, 17 Jul 2022

OATML group members and collaborators are proud to present 11 papers at the ICML 2022 main conference and workshops. Group members are also co-organizing the Workshop on Computational Biology, and the Oxford Wom*n Social.

Conference Papers

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
Sören Mindermann, Jan Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal
Paper: [arxiv]
Spotlight: Thursday 21st, 11:50
Poster: Thursday 21st, 18:00 Poster Session 3

Tranception: Protein Fitness Prediction with Autoregressive Transformers and Inference-time Retrieval
Pascal Notin, Mafalda Dias, Jonathan Frazer, Javier Marchena-Hurtado, Aidan Gomez, Debora S. Marks, Yarin Gal
Spotlight: Wednesday 22nd, 11:40
Poster: Wednesday 22nd, 18:30 Poster Session 2

Continual Learning via Sequential Function-Space Variational Inference
Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal
Paper: Link
Spotlight: Thursday 23rd, 11:25
Poster: Tuesday 21st, 18:30 Poster Session 1

Workshop Papers

Sparse Explanations for Gestational Age Prediction in Fetal Brain Ultrasound
Angus Nicolson, Yarin Gal, Alison Noble
Workshop: 2nd Workshop on Interpretable Machine Learning in Healthcare (IMLH) Saturday 23rd, 9:15 - 17:30

Interventions, Where and How? Bayesian Active Causal Discovery at Scale
Panagiotis Tigas, Yashas Annadani, Andrew Jesson, Bernhard Schölkopf, Yarin Gal, Stefan Bauer
Workshop: Adaptive Experimental Design and Active Learning in the Real World Friday 22nd, 8:40 - 19:30
Paper: arxiv

Path Integral Stochastic Optimal Control for Sampling Transition Paths
Lars Holdijk, Yuanqi Du, Priyank Jaini, Ferry Hooft, Bernd Ensing, Max Welling
Workshop: AI for Science Saturday 23rd, 8:00
Paper: Openreview

RITA: a Study on Scaling Up Generative Protein Sequence Models
Daniel Hesslow, Niccoló Zanichelli, Pascal Notin, Iacopo Poli, Debora Marks
Workshop: Workshop on Computational Biology Friday 22nd
Spotlight Talk: 9:45am
Paper: arxiv

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
Cong Lu, Philip J. Ball, Tim G. J. Rudner, Jack Parker-Holder, Michael A. Osborne, Yee Whye The
Workshop: Workshop on Decision Awareness in Reinforcement Learning, Friday 22nd
Paper: arxiv

Plex: Towards Reliability Using Pretrained Large Model Extensions
Dustin Tran, Jeremiah Liu, Michael W. Dusenberry, Du Phan, Mark Collier, Jie Ren, Kehang Han, Zi Wang, Zelda Mariet, Huiyi Hu, Neil Band, Tim G. J. Rudner, Karan Singhal, Zachary Nado, Joost van Amersfoort, Andreas Kirsch, Rodolphe Jenatton, Nithum Thain, Honglin Yuan, Kelly Buchanan, Kevin Murphy, D. Sculley, Yarin Gal, Zoubin Ghahramani, Jasper Snoek, Balaji Lakshminarayanan
Workshop Contributed Talk at The First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward, Saturday 23rd, 8:00, & Principles of Distribution Shifts (PODS), Saturday 23rd, 9:00.

GeneDisco: A Benchmark for Experimental Design in Drug Discovery
Arash Mehrjou, Ashkan Soleymani, Andrew Jesson, Pascal Notin, Yarin Gal, Stefan Bauer, Patrick Schwab
Workshop: Adaptive Experimental Design and Active Learning in the Real World (ReALML), Friday 22nd, 8:40 - 19:30, Spotlight Talk
Paper: arxiv

Evaluating Online Bayesian Inference in Sample-Based Approximate BNNs
Andreas Kirsch, Jannik Kossen, Yarin Gal
Workshop: Updatable Machine Learning, Saturday 23rd, 8:55 - 17:30
Paper: arxiv


Workshop on Computational Biology
OATML organizers:: Pascal Notin
OATML Program Committee: Neil Band, Freddie Bickford Smith, Jan Brauner, Andreas Kirsch, Lood Van Niekerk
Friday 22nd, 8:30 - 17:30


Oxford Wom*n in Computer Science: Highlighting Women Researchers in ML
OATML organizers: Kelsey Doerksen
Date: Monday 18th, 11:00 - 13:00

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


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