OATML Conference papers at NeurIPS 2022
OATML group members and collaborators are proud to present 8 papers at NeurIPS 2022 main conference, and 11 workshop papers.
Main Conference
In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning
Yiren Zhao, Xitong Gao, Ilia Shumailov, Nicolo Fusi, Robert Mullins
Poster
Rapid Model Architecture Adaption for Meta-Learning ML
Jiaqi Wang, Roei Schuster, Ilia Shumailov, David Lie, Nicolas Papernot
Poster
Scalable Sensitivity and Uncertainty Analyses for Causal-Effect Estimates of Continuous-Valued Interventions
Andrew Jesson, Alyson Douglas, Paul Manshausen, Maëlys Solal, Nicolai Meinshausen, Philip Stier, Yarin Gal, Uri Shalit
Poster
Open High-Resolution Satellite Imagery: the WorldStrat Dataset - with Application to Super-Resolution
Julien Cornebise, Ivan Oršolić, Freddie Kalaitzis
Tractable Function-Space Variational Inference in Bayesian Neural Networks
Tim G. J. Rudner, Zonghao Chen, Yee Whye Teh, Yarin Gal
Interventions, Where and How? Experimental Design for Causal Models at Scale
Panagiotis Tigas, Yashas Annadani, Andrew Jesson, Bernhard Schölkopf, Yarin Gal, Stefan Bauer
Active Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
Jannik Kossen, Sebastian Farquhar, Yarin Gal, Thomas Rainforth
On the Limitations of Stochastic Pre-processing Defenses
Yue Gao, Ilia Shumailov, Kassem Fawaz, Nicolas Papernot
Workshop Papers
DARTFormer: Finding The Best Type Of Attention
Jason Ross Brown, Yiren Zhao, Ilia Shumailov, Robert Mullins
I Can’t Believe it’s not Better Workshop
Wide Attention Is The Way Forward For Transformers
Jason Ross Brown, Yiren Zhao, Ilia Shumailov, Robert Mullins
All Things Attention Workshop
Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
Jannik Kossen, Cătălina Cangea, Eszter Vértes, Andrew Jaegle, Viorica Patraucean, Ira Ktena, Nenad Tomasev, Danielle Belgrave
Foundation Models for Decision Making
TranceptEVE: Combining Family-specific and Family-agnostic Models of Protein Sequences for Improved Fitness Prediction
Pascal Notin, Lodevicus van Niekerk, Aaron Kollasch, Daniel Ritter, Yarin Gal, Debora Marks
Learning Meaningful Representations of Life
Using uncertainty-aware machine learning models to study aerosol-cloud interactions
Maelys Solal, Andrew Jesson, Yarin Gal, Alyson Douglas
Tackling Climate Change with Machine Learning
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Lorenz Kuhn, Yarin Gal, Sebastian Farquhar
ML Safety Workshop
What Out-of-Distribution Is and Is Not
Sebastian Farquhar, Yarin Gal
ML Safety Workshop
Discovering Long-period Exoplanets using Deep Learning with Citizen Science Labels
Shreshth A. Malik, Nora L. Eisner, Chris J. Lintott, Yarin Gal
Machine Learning & the Phsyical Sciences Workshop
SAR-based landslide classification pretraining leads to better segmentation
Ragini Bal Mahesh, Ioannis Prapas, Wei Ji Leong, Vanessa Boehm, Edoardo Nemni, Freddie Kalaitzis, Siddha Ganju, Raul Ramos-Pollán
AI for Humanitarian Assistance and Disaster Response
Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes
Vanessa Boehm, Wei Ji Leong, Ragini Bal Mahesh, Ioannis Prapas, Siddha Ganju, Freddie Kalaitzis, Edoardo Nemni, Raul Ramos-Pollán
Tackling Climate Change with Machine Learning
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?
Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister, Adrien Gaidon, Yarin Gal
Offline Reinforcement Learning Workshop, Causal Machine Learning for Real-World Impact, Workshop on Machine Learning Safety