Picture for Riccardo Grazzi

Riccardo Grazzi

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Add code
Nov 19, 2024
Viaarxiv icon

Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates

Add code
Mar 28, 2024
Viaarxiv icon

Is Mamba Capable of In-Context Learning?

Add code
Feb 05, 2024
Viaarxiv icon

Deep projection networks for learning time-homogeneous dynamical systems

Add code
Jul 19, 2023
Figure 1 for Deep projection networks for learning time-homogeneous dynamical systems
Figure 2 for Deep projection networks for learning time-homogeneous dynamical systems
Figure 3 for Deep projection networks for learning time-homogeneous dynamical systems
Figure 4 for Deep projection networks for learning time-homogeneous dynamical systems
Viaarxiv icon

Group Meritocratic Fairness in Linear Contextual Bandits

Add code
Jun 07, 2022
Figure 1 for Group Meritocratic Fairness in Linear Contextual Bandits
Figure 2 for Group Meritocratic Fairness in Linear Contextual Bandits
Viaarxiv icon

Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start

Add code
Feb 07, 2022
Figure 1 for Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start
Viaarxiv icon

Meta-Forecasting by combining Global Deep Representations with Local Adaptation

Add code
Nov 12, 2021
Figure 1 for Meta-Forecasting by combining Global Deep Representations with Local Adaptation
Figure 2 for Meta-Forecasting by combining Global Deep Representations with Local Adaptation
Figure 3 for Meta-Forecasting by combining Global Deep Representations with Local Adaptation
Figure 4 for Meta-Forecasting by combining Global Deep Representations with Local Adaptation
Viaarxiv icon

Convergence Properties of Stochastic Hypergradients

Add code
Nov 13, 2020
Figure 1 for Convergence Properties of Stochastic Hypergradients
Figure 2 for Convergence Properties of Stochastic Hypergradients
Figure 3 for Convergence Properties of Stochastic Hypergradients
Figure 4 for Convergence Properties of Stochastic Hypergradients
Viaarxiv icon

On the Iteration Complexity of Hypergradient Computation

Add code
Jul 10, 2020
Figure 1 for On the Iteration Complexity of Hypergradient Computation
Figure 2 for On the Iteration Complexity of Hypergradient Computation
Figure 3 for On the Iteration Complexity of Hypergradient Computation
Figure 4 for On the Iteration Complexity of Hypergradient Computation
Viaarxiv icon

Learning-to-Learn Stochastic Gradient Descent with Biased Regularization

Add code
Mar 25, 2019
Figure 1 for Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
Figure 2 for Learning-to-Learn Stochastic Gradient Descent with Biased Regularization
Viaarxiv icon