GERACE, FEDERICA
GERACE, FEDERICA
MAT - DIPARTIMENTO DI MATEMATICA
Ricercatori a tempo determinato
Bias-inducing geometries: An exactly solvable data model with fairness implications
2025 Sarao Mannelli, S.; Gerace, F.; Rostamzadeh, N.; Saglietti, L.
Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks
2025 Szekely, E.; Bardone, L.; Gerace, F.; Goldt, S.
Statistical Mechanics of Transfer Learning in Fully Connected Networks in the Proportional Limit
2025 Ingrosso, A.; Pacelli, R.; Rotondo, P.; Gerace, F.
A distributional simplicity bias in the learning dynamics of transformers
2024 Rende, R.; Gerace, F.; Laio, A.; Goldt, S.
Gaussian universality of perceptrons with random labels
2024 Gerace, Federica; Krzakala, Florent; Loureiro, Bruno; Stephan, Ludovic; Zdeborová, Lenka
Mapping of attention mechanisms to a generalized Potts model
2024 Rende, Riccardo; Gerace, Federica; Laio, Alessandro; Goldt, Sebastian
Probing transfer learning with a model of synthetic correlated datasets
2022 Gerace, Federica; Saglietti, Luca; Sarao Mannelli, Stefano; Saxe, Andrew; Zdeborová, Lenka
Generalisation error in learning with random features and the hidden manifold model
2021 Gerace, Federica; Loureiro, Bruno; Krzakala, Florent; Mézard, Marc; Zdeborová, Lenka
From statistical inference to a differential learning rule for stochastic neural networks
2018 Saglietti, L.; Gerace, F.; Ingrosso, A.; Baldassi, C.; Zecchina, R.
Role of Synaptic Stochasticity in Training Low-Precision Neural Networks
2018 Baldassi, C.; Gerace, F.; Kappen, H. J.; Lucibello, C.; Saglietti, L.; Tartaglione, E.; Zecchina, R.