Diego Granziol
4 papers · 2018–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
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)
generalization bound
(1)
adaptive algorithm
(1)
adaptive optimization
(1)
surrogate model
(1)
scaling law
(1)
adaptive gradient method
(1)
iterate averaging
(1)
quantization error
(1)
batch size
(1)
martingale concentration
(1)
kernel methods
(1)
large language model
(1)
information theory
(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