Picture for Fabrizio Pittorino

Fabrizio Pittorino

FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness

Add code
Feb 29, 2024
Viaarxiv icon

The star-shaped space of solutions of the spherical negative perceptron

Add code
May 18, 2023
Viaarxiv icon

Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry

Add code
Feb 07, 2022
Figure 1 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Figure 2 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Figure 3 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Figure 4 for Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Viaarxiv icon

Deep learning via message passing algorithms based on belief propagation

Add code
Oct 27, 2021
Figure 1 for Deep learning via message passing algorithms based on belief propagation
Figure 2 for Deep learning via message passing algorithms based on belief propagation
Figure 3 for Deep learning via message passing algorithms based on belief propagation
Figure 4 for Deep learning via message passing algorithms based on belief propagation
Viaarxiv icon

Entropic gradient descent algorithms and wide flat minima

Add code
Jun 14, 2020
Figure 1 for Entropic gradient descent algorithms and wide flat minima
Figure 2 for Entropic gradient descent algorithms and wide flat minima
Figure 3 for Entropic gradient descent algorithms and wide flat minima
Figure 4 for Entropic gradient descent algorithms and wide flat minima
Viaarxiv icon

Shaping the learning landscape in neural networks around wide flat minima

Add code
May 21, 2019
Figure 1 for Shaping the learning landscape in neural networks around wide flat minima
Figure 2 for Shaping the learning landscape in neural networks around wide flat minima
Figure 3 for Shaping the learning landscape in neural networks around wide flat minima
Figure 4 for Shaping the learning landscape in neural networks around wide flat minima
Viaarxiv icon