Biroli, Giulio
14 publications
NeurIPS
2025
Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
AISTATS
2024
On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions
ICML
2022
Neural Network Pruning Denoises the Features and Makes Local Connectivity Emerge in Visual Tasks
NeurIPS
2020
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
NeurIPS
2019
Finding the Needle in the Haystack with Convolutions: On the Benefits of Architectural Bias