The loss surfaces of neural networks with general activation functions NP Baskerville, JP Keating, F Mezzadri, J Najnudel Journal of Statistical Mechanics: Theory and Experiment 2021 (6), 064001, 2021 | 29 | 2021 |
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 |
A spin glass model for the loss surfaces of generative adversarial networks NP Baskerville, JP Keating, F Mezzadri, J Najnudel Journal of Statistical Physics 186 (2), 29, 2022 | 15 | 2022 |
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 | 8 | 2022 |
Applicability of random matrix theory in deep learning NP Baskerville, D Granziol, JP Keating arXiv e-prints, arXiv: 2102.06740, 2021 | 6 | 2021 |
A random matrix theory approach to damping in deep learning D Granziol, N Baskerville Journal of Physics: Complexity 3 (2), 024001, 2022 | 3 | 2022 |
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 | | 2024 |
Random matrix theory and the loss surfaces of neural networks NP Baskerville arXiv preprint arXiv:2306.02108, 2023 | | 2023 |
A Novel Sampler for Gauss-Hermite Determinantal Points Processes N Baskerville Available at SSRN 4330239, 2022 | | 2022 |
A novel sampler for Gauss-Hermite determinantal point processes with application to Monte Carlo integration NP Baskerville arXiv preprint arXiv:2203.08061, 2022 | | 2022 |
A Random Matrix Theory Approach to the Adaptive Gradient Generalisation Gap D Granziol, N Baskerville, X Wan, S Albanie, S Roberts stat 1050, 26, 2021 | | 2021 |
A spin-glass model for the loss surfaces of generative adversarial networks. arXiv. https://arxiv. org/abs/2101.02524 NP Baskerville, JP Keating, F Mezzadri, J Najnudel | | 2021 |
A Practical PAC-Bayes Generalisation Bound for Deep Learning D Granziol, M Zhang, N Baskerville | | |