| 2024 | ICLR | Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization. | Ravi Francesco Srinivasan, Francesca Mignacco, Martino Sorbaro, Maria Refinetti, Avi Cooper, Gabriel Kreiman, Giorgia Dellaferrera |
| 2023 | ICML | Neural networks trained with SGD learn distributions of increasing complexity. | Maria Refinetti, Alessandro Ingrosso, Sebastian Goldt |
| 2022 | ICML | Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension. | Bruno Loureiro, Cdric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala |
| 2022 | ICML | The dynamics of representation learning in shallow, non-linear autoencoders. | Maria Refinetti, Sebastian Goldt |
| 2021 | ICML | Align, then memorise: the dynamics of learning with feedback alignment. | Maria Refinetti, Stphane d'Ascoli, Ruben Ohana, Sebastian Goldt |
| 2021 | ICML | Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed. | Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborov |
| 2020 | ICML | Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime. | Stphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala |