Federica Gerace

20 papers A* 4Journal 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Random Matrix Theory of Masked Self-Supervised Regression.
CoRR
Arie Wortsman Zurich, Federica Gerace, Bruno Loureiro, Yue M. Lu
2025 J jnl
Generalization performance of narrow one-hidden layer networks in the teacher-student setting.
CoRR
Jean Barbier, Federica Gerace, Alessandro Ingrosso, Clarissa Lauditi, Enrico M. Malatesta, Gibbs Nwemadji, Rodrigo Pérez Ortiz
2025 J jnl
Testing Transformer Learnability on the Arithmetic Sequence of Rooted Trees.
CoRR
Alessandro Breccia, Federica Gerace, Marco Lippi, Gabriele Sicuro, Pierluigi Contucci
2024 A* conf
A distributional simplicity bias in the learning dynamics of transformers.
NeurIPS
Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
2024 J jnl
A distributional simplicity bias in the learning dynamics of transformers.
CoRR
Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
2024 J jnl
How to choose the right transfer learning protocol? A qualitative analysis in a controlled set-up.
Trans. Mach. Learn. Res.
Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio
2024 A* conf
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks.
NeurIPS
Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt
2023 J jnl
Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks.
CoRR
Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt
2023 J jnl
Optimal inference of a generalised Potts model by single-layer transformers with factored attention.
CoRR
Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
2023 J jnl
Optimal transfer protocol by incremental layer defrosting.
CoRR
Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio
2022 J jnl
Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension.
CoRR
Federica Gerace, Florent Krzakala, Bruno Loureiro, Ludovic Stephan, Lenka Zdeborová
2022 J jnl
Inducing bias is simpler than you think.
CoRR
Stefano Sarao Mannelli, Federica Gerace, Negar Rostamzadeh, Luca Saglietti
2022 J jnl
Probing transfer learning with a model of synthetic correlated datasets.
Mach. Learn. Sci. Technol.
Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová
2021 J jnl
Probing transfer learning with a model of synthetic correlated datasets.
CoRR
Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová
2020 A* conf
Critical initialisation in continuous approximations of binary neural networks.
ICLR
George Stamatescu, Federica Gerace, Carlo Lucibello, Ian G. Fuss, Langford B. White
2020 A* conf
Generalisation error in learning with random features and the hidden manifold model.
ICML
Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2020 J jnl
Generalisation error in learning with random features and the hidden manifold model.
CoRR
Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2019 J jnl
Signal propagation in continuous approximations of binary neural networks.
CoRR
George Stamatescu, Federica Gerace, Carlo Lucibello, Ian G. Fuss, Langford B. White
2018 — —
Statistical physics of neural systems.
Federica Gerace
2017 J jnl
On the role of synaptic stochasticity in training low-precision neural networks.
CoRR
Carlo Baldassi, Federica Gerace, Hilbert J. Kappen, Carlo Lucibello, Luca Saglietti, Enzo Tartaglione, Riccardo Zecchina