Gabriele Perugini

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 13

Top Topics

Belief Propagation

Phase Transition

Top Venues

Mach. Learn. Sci. Technol.

Publications

Silvio Kalaj, Clarissa Lauditi, Gabriele Perugini, Carlo Lucibello, Enrico M. Malatesta, Matteo Negri
Random Features Hopfield Networks generalize retrieval to previously unseen examples. CoRR (2024)
Brandon Livio Annesi, Clarissa Lauditi, Carlo Lucibello, Enrico M. Malatesta, Gabriele Perugini, Fabrizio Pittorino, Luca Saglietti
The star-shaped space of solutions of the spherical negative perceptron. CoRR (2023)
Carlo Baldassi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina
Typical and atypical solutions in non-convex neural networks with discrete and continuous weights. CoRR (2023)
Matteo Negri, Clarissa Lauditi, Gabriele Perugini, Carlo Lucibello, Enrico M. Malatesta
The Hidden-Manifold Hopfield Model and a learning phase transition. CoRR (2023)
Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry. CoRR (2022)
Carlo Lucibello, Fabrizio Pittorino, Gabriele Perugini, Riccardo Zecchina
Deep learning via message passing algorithms based on belief propagation. Mach. Learn. Sci. Technol. 3 (3) (2022)
Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry. ICML (2022)
Carlo Lucibello, Fabrizio Pittorino, Gabriele Perugini, Riccardo Zecchina
Deep learning via message passing algorithms based on belief propagation. CoRR (2021)
Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina
Entropic gradient descent algorithms and wide flat minima. ICLR (2021)
Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina
Unveiling the structure of wide flat minima in neural networks. CoRR (2021)
Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Rosalba Pacelli, Gabriele Perugini, Riccardo Zecchina
Learning through atypical "phase transitions" in overparameterized neural networks. CoRR (2021)
Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Enrico M. Malatesta, Gabriele Perugini, Carlo Baldassi, Matteo Negri, Elizaveta Demyanenko, Riccardo Zecchina
Entropic gradient descent algorithms and wide flat minima. CoRR (2020)
Gabriele Perugini, Federico Ricci-Tersenghi
An improved Belief Propagation algorithm finds many Bethe states in the random field Ising model on random graphs. CoRR (2017)