The Fair Language Model Paradox
A. Pinto, T. Galanti, R. Balestriero
Preprint, Arxiv, 2024

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
L. Ziyin, B. Li, T. Galanti, M. Ueda
Preprint, Arxiv, 2023

Generalization Bounds for Transfer Learning with Pretrained Classifiers
T. Galanti, A. Gyorgy, M. Hutter
Preprint, Arxiv, 2022