Diego Granziol
Title
Cited by
Cited by
Year
Fast information-theoretic Bayesian optimisation
B Ru, MA Osborne, M McLeod, D Granziol
International Conference on Machine Learning, 4384-4392, 2018
302018
Entropic trace estimates for log determinants
J Fitzsimons, D Granziol, K Cutajar, M Osborne, M Filippone, S Roberts
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2017
142017
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
72019
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
72019
Beyond random matrix theory for deep networks
D Granziol
arXiv preprint arXiv:2006.07721, 2020
62020
MLRG deep curvature
D Granziol, X Wan, T Garipov, D Vetrov, S Roberts
arXiv preprint arXiv:1912.09656, 2019
62019
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
D Granziol, S Zohren, S Roberts
arXiv preprint arXiv:2006.09092, 2020
32020
Beyond SGD: Iterate Averaged Adaptive Gradient Method
D Granziol, X Wan, S Albanie, S Roberts
arXiv preprint arXiv:2003.01247, 2020
32020
VBALD-Variational Bayesian approximation of log determinants
D Granziol, E Wagstaff, BX Ru, M Osborne, S Roberts
arXiv preprint arXiv:1802.08054, 2018
22018
Entropic determinants of massive matrices
D Granziol, S Roberts
2017 IEEE International Conference on Big Data (Big Data), 88-93, 2017
22017
Explaining the Adaptive Generalisation Gap
D Granziol, X Wan, S Albanie, S Roberts
arXiv preprint arXiv:2011.08181, 2020
12020
A Maximum Entropy approach to Massive Graph Spectra
D Granziol, R Ru, S Zohren, X Dong, M Osborne, S Roberts
arXiv preprint arXiv:1912.09068, 2019
12019
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
12019
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
12018
MLRG Deep Curvature: An Open-source Package to Analyse and Visualise Neural Network Curvature and Loss Surface
D Granziol, X Wan, T Garipov, D Vetrov, S Roberts
12018
An information and field theoretic approach to the grand canonical ensemble
D Granziol, S Roberts
arXiv preprint arXiv:1703.10099, 2017
12017
Applicability of Random Matrix Theory in Deep Learning
JP Keating, NP Baskerville, D Granziol
arXiv, 2021
2021
Applicability of Random Matrix Theory in Deep Learning
NP Baskerville, D Granziol, JP Keating
arXiv preprint arXiv:2102.06740, 2021
2021
Flatness is a False Friend
D Granziol
arXiv preprint arXiv:2006.09091, 2020
2020
Gadam: Combining Adaptivity with Iterate Averaging Gives Greater Generalisation
D Granziol, X Wan, S Roberts
stat 1050, 10, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–20