Search Results for author: Fabrizio Pittorino

Found 7 papers, 2 papers with code

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

2 code implementations29 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.

Neural Architecture Search

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

no code implementations18 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.

Deep learning via message passing algorithms based on belief propagation

no code implementations27 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.

Continual Learning

Order symmetry breaking and broad distribution of events in spiking neural networks with continuous membrane potential

no code implementations7 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.

Shaping the learning landscape in neural networks around wide flat minima

no code implementations20 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.

Open-Ended Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.