| How deep neural networks learn compositional data: The random hierarchy model F Cagnetta, L Petrini, UM Tomasini, A Favero, M Wyart Physical Review X 14 (3), 031001, 2024 | 30 | 2024 |
| Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data UM Tomasini, A Sclocchi, M Wyart International Conference on Machine Learning, 21548-21583, 2022 | 16* | 2022 |
| How deep convolutional neural networks lose spatial information with training UM Tomasini, L Petrini, F Cagnetta, M Wyart Machine Learning: Science and Technology 4 (4), 045026, 2023 | 9 | 2023 |
| How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model UM Tomasini, M Wyart International Conference on Machine Learning, 48369--48389, 2024 | 8 | 2024 |
| Predictors and predictands of linear response in spatially extended systems UM Tomasini, V Lucarini The European Physical Journal Special Topics 230 (14), 2813-2832, 2021 | 8 | 2021 |
| How data structures affect generalization in Kernel Methods and Deep Learning UM Tomasini EPFL, 2025 | | 2025 |
| Using Observables as Predictors through Response Theory: From Linear Systems to Nonlinear Climate Models UM Tomasini | | 2020 |
| Estensioni centrali e Anomalie in Meccanica Quantistica UM Tomasini | | |