Riccardo Grazzi

24 papers A* 7A 1Journal 15Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Learning State-Tracking from Code Using Linear RNNs.
CoRR
Julien Siems, Riccardo Grazzi, Kirill P. Kalinin, Hitesh Ballani, Babak Rahmani
2025 J jnl
DeltaProduct: Increasing the Expressivity of DeltaNet Through Products of Householders.
CoRR
Julien Siems, Timur Carstensen, Arber Zela, Frank Hutter, Massimiliano Pontil, Riccardo Grazzi
2025 J jnl
OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization.
CoRR
Advait Gadhikar, Riccardo Grazzi, James Hensman
2025 A* conf
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues.
ICLR
Riccardo Grazzi, Julien Siems, Arber Zela, Jörg K. H. Franke, Frank Hutter, Massimiliano Pontil
2024 — conf
Is Mamba Capable of In-Context Learning?
AutoML
Riccardo Grazzi, Julien Niklas Siems, Simon Schrodi, Thomas Brox, Frank Hutter
2024 J jnl
Is Mamba Capable of In-Context Learning?
CoRR
Riccardo Grazzi, Julien Siems, Simon Schrodi, Thomas Brox, Frank Hutter
2024 A* conf
Learning invariant representations of time-homogeneous stochastic dynamical systems.
ICLR
Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi, Karim Lounici, Massimiliano Pontil
2024 A* conf
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates.
ICML
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
2024 J jnl
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates.
CoRR
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
2024 J jnl
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues.
CoRR
Riccardo Grazzi, Julien Siems, Jörg K. H. Franke, Arber Zela, Frank Hutter, Massimiliano Pontil
2023 J jnl
Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start.
J. Mach. Learn. Res.
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
2023 J jnl
Deep projection networks for learning time-homogeneous dynamical systems.
CoRR
Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi, Karim Lounici, Massimiliano Pontil
2022 J jnl
Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start.
CoRR
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
2022 A* conf
Group Meritocratic Fairness in Linear Contextual Bandits.
NeurIPS
Riccardo Grazzi, Arya Akhavan, John Isak Texas Falk, Leonardo Cella, Massimiliano Pontil
2022 J jnl
Group Meritocratic Fairness in Linear Contextual Bandits.
CoRR
Riccardo Grazzi, Arya Akhavan, John Isak Texas Falk, Leonardo Cella, Massimiliano Pontil
2021 A conf
Convergence Properties of Stochastic Hypergradients.
AISTATS
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
2021 J jnl
Meta-Forecasting by combining Global Deep Representations with Local Adaptation.
CoRR
Riccardo Grazzi, Valentin Flunkert, David Salinas, Tim Januschowski, Matthias W. Seeger, Cédric Archambeau
2020 J jnl
Convergence Properties of Stochastic Hypergradients.
CoRR
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
2020 A* conf
On the Iteration Complexity of Hypergradient Computation.
ICML
Riccardo Grazzi, Luca Franceschi, Massimiliano Pontil, Saverio Salzo
2020 J jnl
On the Iteration Complexity of Hypergradient Computation.
CoRR
Riccardo Grazzi, Luca Franceschi, Massimiliano Pontil, Saverio Salzo
2019 A* conf
Learning-to-Learn Stochastic Gradient Descent with Biased Regularization.
ICML
Giulia Denevi, Carlo Ciliberto, Riccardo Grazzi, Massimiliano Pontil
2019 J jnl
Learning-to-Learn Stochastic Gradient Descent with Biased Regularization.
CoRR
Giulia Denevi, Carlo Ciliberto, Riccardo Grazzi, Massimiliano Pontil
2018 A* conf
Bilevel Programming for Hyperparameter Optimization and Meta-Learning.
ICML
Luca Franceschi, Paolo Frasconi, Saverio Salzo, Riccardo Grazzi, Massimiliano Pontil
2018 J jnl
Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning.
CoRR
Luca Franceschi, Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo, Paolo Frasconi