21 OATML Conference and Workshop papers at ICML 2021

Angelos Filos, Clare Lyle, Jannik Kossen, Sebastian Farquhar, Tom Rainforth, Andrew Jesson, Sören Mindermann, Tim G. J. Rudner, Oscar Key, Binxin (Robin) Ru, Pascal Notin, Panagiotis Tigas, Andreas Kirsch, Jishnu Mukhoti, Joost van Amersfoort, Lisa Schut, Muhammed Razzak, Aidan Gomez, Jan Brauner, Yarin Gal, 17 Jul 2021

OATML group members and collaborators are proud to present 21 papers at ICML 2021, including 7 papers at the main conference and 14 papers at various workshops. Group members will also be giving invited talks and participate in panel discussions at the workshops.

Invited Talks and Panel Discussions

Invited talk: Human-in-the-loop Bayesian Deep Learning
Yarin Gal
Workshop: ICML Workshop on Human in the Loop Learning (HILL)
Date: Sat 1:00 p.m. - 1:30 p.m. (BST)

Live Panel Discussion
Yarin Gal
Workshop: Uncertainty and Robustness in Deep Learning
Date: Fri 4:00 p.m. - 5:00 p.m. (BST)

Conference Papers

PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Angelos Filos, Clare Lyle, Yarin Gal, Sergey Levine, Natasha Jaques, Gregory Farquhar
Oral Presentation: Wed Jul 21 01:00 AM – 01:20 AM (BST)
Poster: Wed Jul 21st 03:00 – 06:00 AM (BST)

Active Testing: Sample-Efficient Model Evaluation
Jannik Kossen*, Sebastian Farquhar*, Yarin Gal, Tom Rainforth
Spotlight: Thu Jul 22 03:25 PM – 03:30 PM (BST)
Poster: Thu Jul 22 04:00 PM – 07:00 PM (BST)

Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding
Andrew Jesson, Sören Mindermann, Yarin Gal, Uri Shalit
Spotlight: Thu Jul 22 03:30 AM – 03:35 AM (BST)
Poster: Thu Jul 22 04:00 AM – 07:00 AM (BST)

On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
Tim G. J. Rudner, Oscar Key, Yarin Gal, Tom Rainforth
Spotlight: Thu Jul 22 01:40 PM – 01:45 PM (BST)
Poster: Thu Jul 22 04:00 PM – 07:00 PM (BST)

Deep Adaptive Design: Amortizing Sequential Bayesian Experimental Design
Adam Foster, Desi Ivanova, Ilyas Malik, Tom Rainforth
Oral Presentation: Thu Jul 22 02:00 PM – 02:20 PM (BST)
Poster: Thu Jul 22 04:00 PM – 07:00 PM (BST)

Probabilistic Programs with Stochastic Conditioning
David Tolpin, Yuan Zhou, Tom Rainforth, Hongseok Yang
Spotlight: Thu Jul 22 04:00 AM – 07:00 AM (BST)
Poster: Thu Jul 22 04:00 AM – 07:00 AM (BST)

Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
Xingchen Wan, Vu Nguyen, Huong Ha, Binxin Ru, Cong Lu, Michael A Osborne
Spotlight: Wed Jul 21 02:40 AM – 02:45 AM (BST)
Poster: Wed Jul 21 04:00 AM – 07:00 AM (BST)

Workshops Papers

Viral Evolution and Antibody Escape Mutations using Deep Generative Models
Nicole Thadani, Nathan Rollins, Sarah Gurev, Pascal Notin, Yarin Gal & Debora Marks
Workshop: ICML Workshop on Computational Biology
Date: 8:50-17:30 EDT on Saturday, 24 July 2021
Spotlight Presentation: 14:30-15:15 EDT on Saturday, 24 July 2021

Exploring the latent space of deep generative models: Applications to G-protein coupled receptors
Lood van Niekerk, Sam Berry, Mafalda Dias, Pascal Notin, Jonathan Frazer, Nikki Thadani, Debora Marks and Yarin Gal
Workshop: ICML Workshop on Computational Biology
Date: 8:50-17:30 EDT on Saturday, 24 July 2021

Exploration and preference satisfaction trade-off in reward-free learning
Noor Sajid, Panagiotis Tigas, Alexey Zakharov, Zafeirios Fountas, Karl Friston
Workshop: Unsupervised Reinforcement Learning @ ICML 2021
Date: Fri Jul 23 05:00 AM – 03:00 PM (PDT)

On Pitfalls in OoD Detection: Entropy Considered Harmful
Andreas Kirsch, Jishnu Mukhoti, Joost van Amersfoort, Philip H.S. Torr and Yarin Gal
Workshop: Uncertainty & Robustness in Deep Learning
Date: 9:45am - 10:45am (EST) on Friday, 23 July 2021

Deterministic Neural Networks with Inductive Biases Capture Epistemic and Aleatoric Uncertainty
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H.S. Torr and Yarin Gal
Workshop: Uncertainty & Robustness in Deep Learning
Date: 9:45am - 10:45am (EST) on Friday, 23 July 2021

Deep Deterministic Uncertainty for Semantic Segmentation
Jishnu Mukhoti, Joost van Amersfoort, Philip H.S. Torr, and Yarin Gal
Workshop: Uncertainty & Robustness in Deep Learning
Date: 12 PM - 1 PM (EST), Friday 23 July 2021

Rethinking Function-Space Variational Inference in Bayesian Neural Networks
Tim G. J. Rudner, Zonghao Chen, Yee Whye Teh, Yarin Gal
Workshop: Uncertainty & Robustness in Deep Learning
Date: 12 PM - 1 PM (EST), Friday 23 July 2021

Deep Ensemble Uncertainty Fails as Network Width Increases: Why, and How to Fix It
Lisa Schut, Edward Hu, Greg Yang, and Yarin Gal
Workshop: Uncertainty & Robustness in Deep Learning Date: 12 PM - 1 PM (EST), Friday 23 July 2021

Continual Learning via Function-Space Variational Inference: A Unifying View
Tim G. J. Rudner, Freddie Bickford Smith, Qixuan Feng, Yee Whye Teh, Yarin Gal
Workshop: SubSetML: Subset Selection in Machine Learning: From Theory to Practice
Spotlight Presentation: 12:00 PM - 13:10 PM (PDT) on Saturday, 24 July 2021
Date: 09:00 AM - 09:30 AM (PDT) on Saturday, 24 July 2021
Workshop: Theory and Foundations of Continual Learning
Date: 09:00 AM - 09:30 AM (PDT) on Friday, July 23 2021

Active Learning under Pool Set Distribution Shift and Noisy Data
Andreas Kirsch, Tom Rainforth, Yarin Gal
Workshop: SubSetML: Subset Selection in Machine Learning: From Theory to Practice
Spotlight Presentation: 12:00 PM - 13:10 PM (PDT) on Saturday, 24 July 2021
Date: 09:00 AM - 09:30 AM (PDT) on Saturday, 24 July 2021

Batch Active Learning with Stochastic Acquisition Functions
Andreas Kirsch, Sebastian Farquhar, Yarin Gal
Workshop: SubSetML: Subset Selection in Machine Learning: From Theory to Practice
Spotlight Presentation: 12:00 PM - 13:10 PM (PDT) on Saturday, 24 July 2021
Date: 09:00 AM - 09:30 AM (PDT) on Saturday, 24 July 2021

A Practical Notation for Information-Theoretic Quantities between Outcomes and Random Variables
Andreas Kirsch, Yarin Gal
Workshop: SubSetML: Subset Selection in Machine Learning: From Theory to Practice
Date: 09:00 AM - 09:30 AM (PDT) on Saturday, 24 July 2021

Prioritized training on points that are learnable, worth learning, and not yet learned
Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Brauner, Yarin Gal
Workshop: SubSetML: Subset Selection in Machine Learning: From Theory to Practice
Spotlight Presentation: 12:00 PM - 13:10 PM (PDT) on Saturday, 24 July 2021
Date: 09:00 AM - 09:30 AM (PDT) on Saturday, 24 July 2021

Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
Andrew Jesson, Panagiotis Tigas, Joost van Amersfoort, Andreas Kirsch, Uri Shalit, Yarin Gal
Workshop: The Neglected Assumptions In Causal Inference


More great 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