Diego Granziol

According to our database, Diego Granziol authored at least 22 papers between 2017 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

A Linear Approach to Data Poisoning.

Diego Granziol, Donald Flynn

CoRR, May, 2025

HessFormer: Hessians at Foundation Scale.

Diego Granziol

CoRR, May, 2025

Compute-Optimal LLMs Provably Generalize Better with Scale.

Marc Anton Finzi, Sanyam Kapoor, Diego Granziol, Anming Gu, Christopher De Sa, J. Zico Kolter, Andrew Gordon Wilson

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Iterate Averaging in the Quest for Best Test Error.

Diego Granziol, Nicholas P. Baskerville, Xingchen Wan, Samuel Albanie, Stephen Roberts

J. Mach. Learn. Res., 2024

2022

Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training.

Diego Granziol, Stefan Zohren, Stephen Roberts

J. Mach. Learn. Res., 2022

Universal characteristics of deep neural network loss surfaces from random matrix theory.

Nicholas P. Baskerville, Jonathan P. Keating, Francesco Mezzadri, Joseph Najnudel, Diego Granziol

CoRR, 2022

Maximum Entropy Approach to Massive Graph Spectrum Learning with Applications.

Diego Granziol, Binxin Ru, Xiaowen Dong, Stefan Zohren, Michael A. Osborne, Stephen J. Roberts

Algorithms, 2022

2021

Applicability of Random Matrix Theory in Deep Learning.

Nicholas P. Baskerville, Diego Granziol, Jonathan P. Keating

CoRR, 2021

2020

Spectral machine learning.

Diego Granziol

PhD thesis, 2020

Explaining the Adaptive Generalisation Gap.

Diego Granziol, Samuel Albanie, Xingchen Wan, Stephen J. Roberts

CoRR, 2020

Curvature is Key: Sub-Sampled Loss Surfaces and the Implications for Large Batch Training.

Diego Granziol

CoRR, 2020

Flatness is a False Friend.

Diego Granziol

CoRR, 2020

Beyond Random Matrix Theory for Deep Networks.

Diego Granziol

CoRR, 2020

Iterate Averaging Helps: An Alternative Perspective in Deep Learning.

Diego Granziol, Xingchen Wan, Stephen Roberts

CoRR, 2020

2019

MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning.

Diego Granziol, Bin Xin Ru, Stefan Zohren, Xiaowen Dong, Michael A. Osborne, Stephen J. Roberts

Entropy, 2019

MLRG Deep Curvature.

Diego Granziol, Xingchen Wan, Timur Garipov, Dmitry P. Vetrov, Stephen Roberts

CoRR, 2019

A Maximum Entropy approach to Massive Graph Spectra.

Diego Granziol, Robin Ru, Stefan Zohren, Xiaowen Dong, Michael A. Osborne, Stephen J. Roberts

CoRR, 2019

2018

Entropic Spectral Learning in Large Scale Networks.

Diego Granziol, Bin Xin Ru, Stefan Zohren, Xiaowen Dong, Michael A. Osborne, Stephen J. Roberts

CoRR, 2018

VBALD - Variational Bayesian Approximation of Log Determinants.

Diego Granziol, Edward Wagstaff, Bin Xin Ru, Michael A. Osborne, Stephen J. Roberts

CoRR, 2018

Fast Information-theoretic Bayesian Optimisation.

Bin Xin Ru, Mark McLeod, Diego Granziol, Michael A. Osborne

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Entropic Trace Estimates for Log Determinants.

Jack K. Fitzsimons, Diego Granziol, Kurt Cutajar, Michael A. Osborne, Maurizio Filippone, Stephen J. Roberts

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2017

Entropic determinants of massive matrices.

Diego Granziol, Stephen J. Roberts

Proceedings of the 2017 IEEE International Conference on Big Data (IEEE BigData 2017), 2017