Three factors influencing minima in sgd S Jastrzębski, Z Kenton, D Arpit, N Ballas, A Fischer, Y Bengio, A Storkey
arXiv preprint arXiv:1711.04623, 2017
439 2017 Ethical and social risks of harm from language models L Weidinger, J Mellor, M Rauh, C Griffin, J Uesato, PS Huang, M Cheng, ...
arXiv preprint arXiv:2112.04359, 2021
399 2021 Taxonomy of risks posed by language models L Weidinger, J Uesato, M Rauh, C Griffin, PS Huang, J Mellor, A Glaese, ...
Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022
187 2022 A systematic comparison of Bayesian deep learning robustness in diabetic retinopathy tasks A Filos, S Farquhar, AN Gomez, TGJ Rudner, Z Kenton, L Smith, ...
arXiv preprint arXiv:1912.10481, 2019
96 2019 On the relation between the sharpest directions of DNN loss and the SGD step length S Jastrzębski, Z Kenton, N Ballas, A Fischer, Y Bengio, A Storkey
arXiv preprint arXiv:1807.05031, 2018
94 2018 Alignment of language agents Z Kenton, T Everitt, L Weidinger, I Gabriel, V Mikulik, G Irving
arXiv preprint arXiv:2103.14659, 2021
79 2021 Specification gaming: the flip side of AI ingenuity V Krakovna, J Uesato, V Mikulik, M Rahtz, T Everitt, R Kumar, Z Kenton, ...
DeepMind Blog 3, 2020
78 2020 Imitating interactive intelligence J Abramson, A Ahuja, I Barr, A Brussee, F Carnevale, M Cassin, ...
arXiv preprint arXiv:2012.05672, 2020
56 2020 The squeezed limit of the bispectrum in multi-field inflation Z Kenton, DJ Mulryne
Journal of Cosmology and Astroparticle Physics 2015 (10), 018, 2015
39 2015 D-brane potentials in the warped resolved conifold and natural inflation Z Kenton, S Thomas
Journal of High Energy Physics 2015 (2), 1-42, 2015
36 2015 Finding flatter minima with sgd S Jastrzębski, Z Kenton, D Arpit, N Ballas, A Fischer, Y Bengio, A Storkey
32 2018 Goal misgeneralization: Why correct specifications aren't enough for correct goals R Shah, V Varma, R Kumar, M Phuong, V Krakovna, J Uesato, Z Kenton
arXiv preprint arXiv:2210.01790, 2022
27 2022 Generalizing from a few environments in safety-critical reinforcement learning Z Kenton, A Filos, Y Gal, O Evans
Safe Machine Learning workshop at ICLR, 2019
23 * 2019 Width of minima reached by stochastic gradient descent is influenced by learning rate to batch size ratio S Jastrzębski, Z Kenton, D Arpit, N Ballas, A Fischer, Y Bengio, A Storkey
Artificial Neural Networks and Machine Learning–ICANN 2018: 27th …, 2018
23 2018 The separate universe approach to soft limits Z Kenton, DJ Mulryne
Journal of Cosmology and Astroparticle Physics 2016 (10), 035, 2016
22 2016 Generating the cosmic microwave background power asymmetry with Z Kenton, DJ Mulryne, S Thomas
Physical Review D 92 (2), 023505, 2015
20 2015 Benchmarking Bayesian deep learning with diabetic retinopathy diagnosis A Filos, S Farquhar, AN Gomez, TGJ Rudner, Z Kenton, L Smith, ...
Preprint at https://arxiv. org/abs/1912.10481, 2019
19 2019 Predicting Human Deliberative Judgments with Machine Learning O Evans, A Stuhlmüller, C Cundy, R Carey, Z Kenton, T McGrath, ...
https://zackenton.github.io/files/predicting_judgments_final.pdf, 2018
13 2018 DNN's Sharpest Directions Along the SGD Trajectory S Jastrzębski, Z Kenton, N Ballas, A Fischer, Y Bengio, A Storkey
Modern Trends in Nonconvex Optimization for Machine Learning Workshop (ICML …, 2018
9 * 2018 Discovering agents Z Kenton, R Kumar, S Farquhar, J Richens, M MacDermott, T Everitt
Artificial Intelligence, 103963, 2023
8 2023 
Amos StorkeyProfessor of Machine Learning and AI, School of Informatics, University of Edinburgh, UKZweryfikowany adres z ed.ac.uk
