Papers:
(2024) How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model, Tomasini U.M. and Wyart M., arXiv:2404.10727, ICML 2024.
(2023) How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model, Petrini L., Cagnetta F., Tomasini U.M., Favero A. and Wyart M. arXiv:2307.02129, Under Review.
(2022) How deep convolutional neural networks lose spatial information with training, Tomasini U.M., Petrini L., Cagnetta F. and Wyart M., Machine Learning: Science and Technology (2023).
(2022) Failure and success of the spectral bias prediction for Laplace Kernel Ridge Regression: the case of low-dimensional data, Tomasini U.M., Sclocchi A. and Wyart M., ICML 2022 (Spotlight).
(2021) Predictors and Predictands of Linear Response in Spatially Extended Systems, Tomasini U.M. and Lucarini V., Eur. Phys. J. Spec. Top. (2021).
Thesis:
(2020) Master: Using Observables as Predictors through Response Theory: From Linear Systems to Nonlinear Climate Models, UniPD.
(2018) Bachelor: Estensioni centrali e Anomalie in Meccanica Quantistica, UniPD.