Joost van Amersfoort

17 papers A* 5Journal 12

Year	Rank	Type	Title / Venue / Authors
2023	A*	`conf`	Deep Deterministic Uncertainty: A New Simple Baseline. CVPR Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal
2022	J	`jnl`	Mixtures of large-scale dynamic functional brain network modes. NeuroImage Chetan Gohil, Evan Roberts, Ryan C. Timms, Alex Skates, Cameron Higgins, Andrew Quinn, Usama Pervaiz, Joost van Amersfoort, Pascal Notin, Yarin Gal, Stanislaw Adaszewski, Mark W. Woolrich
2022	J	`jnl`	Plex: Towards Reliability using Pretrained Large Model Extensions. CoRR Dustin Tran, Jeremiah Z. 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
2022	A*	`conf`	Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients. ICLR Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal
2022	J	`jnl`	Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients. CoRR Milad Alizadeh, Shyam A. Tailor, Luisa M. Zintgraf, Joost van Amersfoort, Sebastian Farquhar, Nicholas Donald Lane, Yarin Gal
2021	J	`jnl`	Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective. CoRR Lewis Smith, Joost van Amersfoort, Haiwen Huang, Stephen J. Roberts, Yarin Gal
2021	A*	`conf`	Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data. NeurIPS Andrew Jesson, Panagiotis Tigas, Joost van Amersfoort, Andreas Kirsch, Uri Shalit, Yarin Gal
2021	J	`jnl`	Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data. CoRR Andrew Jesson, Panagiotis Tigas, Joost van Amersfoort, Andreas Kirsch, Uri Shalit, Yarin Gal
2021	J	`jnl`	Decomposing Representations for Deterministic Uncertainty Estimation. CoRR Haiwen Huang, Joost van Amersfoort, Yarin Gal
2021	J	`jnl`	Deep Deterministic Uncertainty for Semantic Segmentation. CoRR Jishnu Mukhoti, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal
2021	J	`jnl`	Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty. CoRR Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort, Philip H. S. Torr, Yarin Gal
2021	J	`jnl`	Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression. CoRR Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal
2020	J	`jnl`	Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network. CoRR Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal
2020	J	`jnl`	Single Shot Structured Pruning Before Training. CoRR Joost van Amersfoort, Milad Alizadeh, Sebastian Farquhar, Nicholas D. Lane, Yarin Gal
2020	A*	`conf`	Uncertainty Estimation Using a Single Deep Deterministic Neural Network. ICML Joost van Amersfoort, Lewis Smith, Yee Whye Teh, Yarin Gal
2019	A*	`conf`	BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning. NeurIPS Andreas Kirsch, Joost van Amersfoort, Yarin Gal
2019	J	`jnl`	BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning. CoRR Andreas Kirsch, Joost van Amersfoort, Yarin Gal