Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Riccardo Grazzi
Observed names:
Grazzi R,
Grazzi, Riccardo
Institutions:
Microsoft (United States),
Microsoft Research (United Kingdom)
Observed institutions:
Microsoft (United States),
Italian Institute of Technology,
Microsoft Research (United Kingdom),
ELLIS Institute Tübingen,
University College London
OpenAlex ID:
A5034665821
Bilevel Programming for Hyperparameter Optimization and Meta-Learning
2018
·
Franceschi, Luca
, Frasconi, Paolo
, et al.
·
arXiv (Cornell University)
·
274
PDF
Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
2019
·
Denevi, Giulia
, Ciliberto, Carlo
, et al.
·
arXiv (Cornell University)
·
54
PDF
On the Iteration Complexity of Hypergradient Computation
2020
·
Grazzi, Riccardo
, Franceschi, Luca
, et al.
·
arXiv (Cornell University)
·
49
PDF
On the Iteration Complexity of Hypergradient Computations
2020
·
Riccardo Grazzi
, Saverio Salzo
, et al.
·
International Conference on Machine Learning
·
15
Is Mamba Capable of In-Context Learning?
2024
·
Grazzi, Riccardo
, Siems, Julien
, et al.
·
arXiv (Cornell University)
·
11
PDF
Group Meritocratic Fairness in Linear Contextual Bandits
2022
·
Riccardo Grazzi
, Arya Akhavan
, et al.
·
neural information processing systems
·
5
PDF
Convergence Properties of Stochastic Hypergradients
2020
·
Grazzi, Riccardo
, Pontil, Massimiliano
, et al.
·
arXiv (Cornell University)
·
5
PDF
Meta-Forecasting by combining Global Deep Representations with Local Adaptation
2021
·
Grazzi, Riccardo
, Flunkert, Valentin
, et al.
·
arXiv (Cornell University)
·
2
PDF
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
2024
·
Grazzi, Riccardo
, Siems, Julien
, et al.
·
arXiv (Cornell University)
·
1
PDF
Learning invariant representations of time-homogeneous stochastic dynamical systems
2023
·
Kostic, Vladimir R.
, Novelli, Pietro
, et al.
·
arXiv (Cornell University)
·
1
PDF
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning
2018
·
Franceschi, Luca
, Grazzi, Riccardo
, et al.
·
arXiv (Cornell University)
·
1
PDF
Beyond 4 bits: Data-Centric Post-training Quantization and Recovery
2026
·
Sukthanker, Rhea Sanjay
, Grazzi, Riccardo
, et al.
·
arXiv (Cornell University)
PDF
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
2026
·
Scholten, Yan
, Lawrence, Rachel
, et al.
·
arXiv (Cornell University)
PDF
Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention
2026
·
Siems, Julien
, Grazzi, Riccardo
, et al.
·
arXiv (Cornell University)
PDF
Bilevel learning
2026
·
Grazzi, Riccardo
, Pontil, Massimiliano
, et al.
·
arXiv (Cornell University)
PDF
Learning State-Tracking from Code Using Linear RNNs
2026
·
Siems, Julien
, Grazzi, Riccardo
, et al.
·
arXiv (Cornell University)
PDF
OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization
2025
·
Gadhikar, Advait
, Grazzi, Riccardo
, et al.
·
arXiv (Cornell University)
PDF
DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products
2025
·
Julien Siems
, Timur Carstensen
, et al.
·
neural information processing systems
PDF
Show more works
View as search
Works count:
23
Citation count:
418
H-index:
5
I10-index:
5
Year
Topic
Type
