Granziol, Diego

6 publications

ICLR 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

JMLR 2024 Iterate Averaging in the Quest for Best Test Error Diego Granziol, Nicholas P. Baskerville, Xingchen Wan, Samuel Albanie, Stephen Roberts

JMLR 2022 Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training Diego Granziol, Stefan Zohren, Stephen Roberts

ICLR 2020 Towards Understanding the True Loss Surface of Deep Neural Networks Using Random Matrix Theory and Iterative Spectral Methods Diego Granziol, Timur Garipov, Dmitry Vetrov, Stefan Zohren, Stephen Roberts, Andrew Gordon Wilson

ICML 2018 Fast Information-Theoretic Bayesian Optimisation Binxin Ru, Michael A. Osborne, Mark Mcleod, Diego Granziol

ECML-PKDD 2017 Entropic Trace Estimates for Log Determinants Jack K. Fitzsimons, Diego Granziol, Kurt Cutajar, Michael A. Osborne, Maurizio Filippone, Stephen J. Roberts