Follow
Clare Lyle
Clare Lyle
University of Oxford
Verified email at deepmind.com - Homepage
Title
Cited by
Cited by
Year
The malicious use of artificial intelligence: Forecasting, prevention, and mitigation
M Brundage, S Avin, J Clark, H Toner, P Eckersley, B Garfinkel, A Dafoe, ...
arXiv preprint arXiv:1802.07228, 2018
8322018
Invariant causal prediction for block mdps
A Zhang, C Lyle, S Sodhani, A Filos, M Kwiatkowska, J Pineau, Y Gal, ...
International Conference on Machine Learning, 11214-11224, 2020
1042020
A geometric perspective on optimal representations for reinforcement learning
MG Bellemare, W Dabney, R Dadashi, AA Taiga, PS Castro, NL Roux, ...
NeurIPS 2019, 2019
922019
A comparative analysis of expected and distributional reinforcement learning
C Lyle, MG Bellemare, PS Castro
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 4504-4511, 2019
822019
On the benefits of invariance in neural networks
C Lyle, M van der Wilk, M Kwiatkowska, Y Gal, B Bloem-Reddy
arXiv preprint arXiv:2005.00178, 2020
76*2020
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
J Kossen, N Band, C Lyle, AN Gomez, T Rainforth, Y Gal
NeurIPS 2021, 2021
642021
On The Effect of Auxiliary Tasks on Representation Dynamics
C Lyle, M Rowland, G Ostrovski, W Dabney
AISTATS 2021, 2021
552021
Understanding and preventing capacity loss in reinforcement learning
C Lyle, M Rowland, W Dabney
arXiv preprint arXiv:2204.09560, 2022
432022
A Speedy Performance Estimator for Neural Architecture Search
B Ru, C Lyle, L Schut, M van der Wilk, Y Gal
NeurIPS 2021, 2020
42*2020
The malicious use of artificial intelligence: forecasting, prevention, and mitigation. 2018
M Brundage, S Avin, J Clark, H Toner, P Eckersley, B Garfinkel, A Dafoe, ...
arXiv preprint arXiv:1802.07228, 1802
251802
A Bayesian Perspective on Training Speed and Model Selection
C Lyle, L Schut, B Ru, Y Gal, M van der Wilk
Proceedings of the 33rd International Conference on Neural Information …, 2020
222020
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
A Filos, C Lyle, Y Gal, S Levine, N Jaques, G Farquhar
ICML 2021, 2021
172021
The Malicious use of artificial intelligence: forecasting, prevention, and mitigation authors are listed in order of contribution design direction
S Bhatnagar, T Cotton, M Brundage, S Avin, J Clark, H Toner, P Eckersley, ...
arXiv Prepr. arXiv1802 7228, 101, 2018
162018
Gan q-learning
T Doan, B Mazoure, C Lyle
arXiv preprint arXiv:1805.04874, 2018
152018
Understanding plasticity in neural networks
C Lyle, Z Zheng, E Nikishin, BA Pires, R Pascanu, W Dabney
arXiv preprint arXiv:2303.01486, 2023
142023
Unpacking information bottlenecks: Unifying information-theoretic objectives in deep learning
A Kirsch, C Lyle, Y Gal
arXiv preprint arXiv:2003.12537, 2020
132020
Understanding self-predictive learning for reinforcement learning
Y Tang, ZD Guo, PH Richemond, BA Pires, Y Chandak, R Munos, ...
International Conference on Machine Learning, 33632-33656, 2023
112023
Learning dynamics and generalization in deep reinforcement learning
C Lyle, M Rowland, W Dabney, M Kwiatkowska, Y Gal
International Conference on Machine Learning, 14560-14581, 2022
102022
Robustness to pruning predicts generalization in deep neural networks
L Kuhn, C Lyle, AN Gomez, J Rothfuss, Y Gal
arXiv preprint arXiv:2103.06002, 2021
92021
The malicious use of artificial intelligence: Forecasting, prevention, and mitigation. arXiv. org, vol. cs
M Brundage, S Avin, J Clark, H Toner, P Eckersley, B Garfinkel, A Dafoe, ...
AI, 2018
82018
The system can't perform the operation now. Try again later.
Articles 1–20