35 citations · 115 across the 10 of their papers we have counts for
4 papers · 1 filter
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry
Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini +3
We systematize the approach to the investigation of deep neural network landscapes by basing it on the geometry of the space of implemented functions rather than the space of param…
Deep learning via message passing algorithms based on belief propagation
Carlo Lucibello, Fabrizio Pittorino, Gabriele Perugini +1
Message-passing algorithms based on the Belief Propagation (BP) equations constitute a well-known distributed computational scheme. It is exact on tree-like graphical models and ha…
Learning through atypical "phase transitions" in overparameterized neural networks
Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta +3
Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient…
Entropic gradient descent algorithms and wide flat minima
Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer +4
The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time. Increasing evidence suggests they possess better generalization ca…