2 code implementations • 29 Feb 2024 • Matteo Gambella, Fabrizio Pittorino, Manuel Roveri
FlatNAS achieves a good trade-off between performance, OOD generalization, and the number of parameters, by using only in-distribution data in the NAS exploration.
no code implementations • 18 May 2023 • Brandon Livio Annesi, Clarissa Lauditi, Carlo Lucibello, Enrico M. Malatesta, Gabriele Perugini, Fabrizio Pittorino, Luca Saglietti
Empirical studies on the landscape of neural networks have shown that low-energy configurations are often found in complex connected structures, where zero-energy paths between pairs of distant solutions can be constructed.
no code implementations • 7 Feb 2022 • Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina
This lets us derive a meaningful notion of the flatness of minimizers and of the geodesic paths connecting them.
no code implementations • 27 Oct 2021 • Carlo Lucibello, Fabrizio Pittorino, Gabriele Perugini, Riccardo Zecchina
Message-passing algorithms based on the Belief Propagation (BP) equations constitute a well-known distributed computational scheme.
no code implementations • 7 Apr 2021 • Marco Stucchi, Fabrizio Pittorino, Matteo di Volo, Alessandro Vezzani, Raffaella Burioni
We introduce an exactly integrable version of the well-known leaky integrate-and-fire (LIF) model, with continuous membrane potential at the spiking event, the c-LIF.
1 code implementation • ICLR 2021 • Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina
The properties of flat minima in the empirical risk landscape of neural networks have been debated for some time.
no code implementations • 20 May 2019 • Carlo Baldassi, Fabrizio Pittorino, Riccardo Zecchina
In the case of SGD and cross-entropy loss, we show that a slow reduction of the norm of the weights along the learning process also leads to WFM.