Saglietti, Luca

8 publications

ICML 2025 How Transformers Learn Structured Data: Insights from Hierarchical Filtering Jerome Garnier-Brun, Marc Mezard, Emanuele Moscato, Luca Saglietti

NeurIPS 2025 On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study Riccardo Alberghi, Elizaveta Demyanenko, Luca Biggio, Luca Saglietti

ICMLW 2024 Bias-Inducing Geometries: Exactly Solvable Data Model with Fairness Implications Stefano Sarao Mannelli, Federica Gerace, Negar Rostamzadeh, Luca Saglietti

TMLR 2024 How to Choose the Right Transfer Learning Protocol? a Qualitative Analysis in a Controlled Set-up Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio

ICML 2024 Tilting the Odds at the Lottery: The Interplay of Overparameterisation and Curricula in Neural Networks Stefano Sarao Mannelli, Yaraslau Ivashynka, Andrew M Saxe, Luca Saglietti

NeurIPS 2022 An Analytical Theory of Curriculum Learning in Teacher-Student Networks Luca Saglietti, Stefano Mannelli, Andrew Saxe

ICML 2019 Generalized Approximate Survey Propagation for High-Dimensional Estimation Carlo Lucibello, Luca Saglietti, Yue Lu

NeurIPS 2018 Gaussian Process Prior Variational Autoencoders Francesco Paolo Casale, Adrian Dalca, Luca Saglietti, Jennifer Listgarten, Nicolo Fusi