Diego Granziol
4 papers · 2018–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (3) π Academic Marathon (7) π Cross-Pollinator (10) πΊοΈ Taxonomy Completionist (11)
π£
Hot Topic Early Bird
Conferences
JMLR (2)
ICLR (1)
ICML (1)
Top co-authors
Keywords
learning rate
(2)
stochastic gradient descent
(1)
neural network training
(1)
expected improvement
(1)
hessian matrix
(1)
bayesian optimization
(1)
random matrix theory
(1)
adaptive algorithm
(1)
adaptive optimization
(1)
surrogate model
(1)
adaptive gradient method
(1)
iterate averaging
(1)
batch size
(1)
information theory
(1)
kernel methods
(1)
Papers
Compute-Optimal LLMs Provably Generalize Better with Scale
ICLR 2025
Iterate Averaging in the Quest for Best Test Error
JMLR 2024
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
JMLR 2022
Fast Information-theoretic Bayesian Optimisation
ICML 2018