Gabriele Perugini

According to our database, Gabriele Perugini authored at least 10 papers between 2017 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

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

Brandon Livio Annesi, Clarissa Lauditi, Carlo Lucibello, Enrico M. Malatesta, Gabriele Perugini, Fabrizio Pittorino, Luca Saglietti

CoRR, 2023

Typical and atypical solutions in non-convex neural networks with discrete and continuous weights.

Carlo Baldassi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina

CoRR, 2023

The Hidden-Manifold Hopfield Model and a learning phase transition.

Matteo Negri, Clarissa Lauditi, Gabriele Perugini, Carlo Lucibello, Enrico M. Malatesta

CoRR, 2023

2022

Deep learning via message passing algorithms based on belief propagation.

Carlo Lucibello, Fabrizio Pittorino, Gabriele Perugini, Riccardo Zecchina

Mach. Learn. Sci. Technol., 2022

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

Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina

Proceedings of the International Conference on Machine Learning, 2022

2021

Learning through atypical "phase transitions" in overparameterized neural networks.

Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Rosalba Pacelli, Gabriele Perugini, Riccardo Zecchina

CoRR, 2021

Unveiling the structure of wide flat minima in neural networks.

Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina

CoRR, 2021

Entropic gradient descent algorithms and wide flat minima.

Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Entropic gradient descent algorithms and wide flat minima.

Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Enrico M. Malatesta, Gabriele Perugini, Carlo Baldassi, Matteo Negri, Elizaveta Demyanenko, Riccardo Zecchina

CoRR, 2020

2017

An improved Belief Propagation algorithm finds many Bethe states in the random field Ising model on random graphs.

Gabriele Perugini, Federico Ricci-Tersenghi

CoRR, 2017