Picture for Francesca Mignacco

Francesca Mignacco

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory

Add code
Sep 26, 2024
Figure 1 for Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
Figure 2 for Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
Figure 3 for Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
Figure 4 for Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
Viaarxiv icon

Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers

Add code
May 24, 2024
Viaarxiv icon

Nonlinear classification of neural manifolds with contextual information

Add code
May 10, 2024
Figure 1 for Nonlinear classification of neural manifolds with contextual information
Figure 2 for Nonlinear classification of neural manifolds with contextual information
Figure 3 for Nonlinear classification of neural manifolds with contextual information
Figure 4 for Nonlinear classification of neural manifolds with contextual information
Viaarxiv icon

Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization

Add code
Feb 10, 2023
Viaarxiv icon

Rigorous dynamical mean field theory for stochastic gradient descent methods

Add code
Oct 12, 2022
Figure 1 for Rigorous dynamical mean field theory for stochastic gradient descent methods
Figure 2 for Rigorous dynamical mean field theory for stochastic gradient descent methods
Figure 3 for Rigorous dynamical mean field theory for stochastic gradient descent methods
Viaarxiv icon

Learning curves for the multi-class teacher-student perceptron

Add code
Mar 22, 2022
Figure 1 for Learning curves for the multi-class teacher-student perceptron
Figure 2 for Learning curves for the multi-class teacher-student perceptron
Figure 3 for Learning curves for the multi-class teacher-student perceptron
Figure 4 for Learning curves for the multi-class teacher-student perceptron
Viaarxiv icon

The effective noise of Stochastic Gradient Descent

Add code
Dec 20, 2021
Figure 1 for The effective noise of Stochastic Gradient Descent
Figure 2 for The effective noise of Stochastic Gradient Descent
Figure 3 for The effective noise of Stochastic Gradient Descent
Figure 4 for The effective noise of Stochastic Gradient Descent
Viaarxiv icon

Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem

Add code
Mar 08, 2021
Figure 1 for Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
Figure 2 for Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
Figure 3 for Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
Figure 4 for Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem
Viaarxiv icon

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Add code
Jun 10, 2020
Figure 1 for Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
Figure 2 for Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
Figure 3 for Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
Figure 4 for Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification
Viaarxiv icon

The role of regularization in classification of high-dimensional noisy Gaussian mixture

Add code
Feb 26, 2020
Figure 1 for The role of regularization in classification of high-dimensional noisy Gaussian mixture
Figure 2 for The role of regularization in classification of high-dimensional noisy Gaussian mixture
Figure 3 for The role of regularization in classification of high-dimensional noisy Gaussian mixture
Figure 4 for The role of regularization in classification of high-dimensional noisy Gaussian mixture
Viaarxiv icon