| Fast information-theoretic Bayesian optimisation B Ru, MA Osborne, M McLeod, D Granziol International Conference on Machine Learning, 4384-4392, 2018 | 57 | 2018 |
| Learning rates as a function of batch size: A random matrix theory approach to neural network training D Granziol, S Zohren, S Roberts Journal of Machine Learning Research 23 (173), 1-65, 2022 | 40 | 2022 |
| Entropic trace estimates for log determinants J Fitzsimons, D Granziol, K Cutajar, M Osborne, M Filippone, S Roberts Machine Learning and Knowledge Discovery in Databases: European Conference …, 2017 | 26 | 2017 |
| MEMe: An accurate maximum entropy method for efficient approximations in large-scale machine learning D Granziol, B Ru, S Zohren, X Dong, M Osborne, S Roberts Entropy 21 (6), 551, 2019 | 19 | 2019 |
| Beyond random matrix theory for deep networks D Granziol arXiv preprint arXiv:2006.07721, 2020 | 17 | 2020 |
| Towards understanding the true loss surface of deep neural networks using random matrix theory and iterative spectral methods D Granziol, T Garipov, D Vetrov, S Zohren, S Roberts, AG Wilson | 16 | 2019 |
| Appearance of random matrix theory in deep learning NP Baskerville, D Granziol, JP Keating Physica A: Statistical Mechanics and its Applications 590, 126742, 2022 | 15 | 2022 |
| MLRG deep curvature D Granziol, X Wan, T Garipov, D Vetrov, S Roberts arXiv preprint arXiv:1912.09656, 2019 | 14 | 2019 |
| Flatness is a false friend D Granziol arXiv preprint arXiv:2006.09091, 2020 | 12 | 2020 |
| Iterate Averaging in the Quest for Best Test Error D Granziol, NP Baskerville, X Wan, S Albanie, S Roberts Journal of Machine Learning Research 25 (20), 1-55, 2024 | 11* | 2024 |
| Universal characteristics of deep neural network loss surfaces from random matrix theory NP Baskerville, JP Keating, F Mezzadri, J Najnudel, D Granziol Journal of Physics A: Mathematical and Theoretical 55 (49), 494002, 2022 | 6 | 2022 |
| Applicability of random matrix theory in deep learning NP Baskerville, D Granziol, JP Keating arXiv e-prints, arXiv: 2102.06740, 2021 | 6 | 2021 |
| Deep curvature suite D Granziol, X Wan, T Garipov arXiv preprint arXiv:1912.09656, 2019 | 5 | 2019 |
| Explaining the Adapative Generalisation Gap D Granziol, S Albanie, X Wan, S Roberts stat 1050, 15, 2020 | 4 | 2020 |
| A random matrix theory approach to damping in deep learning D Granziol, N Baskerville Journal of Physics: Complexity 3 (2), 024001, 2022 | 3 | 2022 |
| Ranker-agnostic contextual position bias estimation OB Mayor, V Bellini, A Buchholz, G Di Benedetto, DM Granziol, M Ruffini, ... arXiv preprint arXiv:2107.13327, 2021 | 3 | 2021 |
| Gadam: Combining adaptivity with iterate averaging gives greater generalisation D Granziol, X Wan, S Roberts stat 1050, 10, 2020 | 3 | 2020 |
| VBALD-Variational Bayesian approximation of log determinants D Granziol, E Wagstaff, BX Ru, M Osborne, S Roberts arXiv preprint arXiv:1802.08054, 2018 | 3 | 2018 |
| The Deep Learning Limit: are negative neural network eigenvalues just noise? D Granziol, T Garipov, S Zohren, D Vetrov, S Roberts, AG Wilson ICML 2019 workshop on theoretical physics for deep learning, 2019 | 2 | 2019 |
| Entropic spectral learning for large-scale graphs D Granziol, B Ru, S Zohren, X Dong, M Osborne, S Roberts arXiv preprint arXiv:1804.06802, 2018 | 2 | 2018 |
Stephen RobertsProfessor of Engineering Science (Machine Learning, Information Engineering), University of OxfordVerified email at robots.ox.ac.uk
