26 citations · 137 across the 41 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
stat.ML2024
Privacy for Free in the Overparameterized Regime
Simone Bombari, Marco Mondelli
Differentially private gradient descent (DP-GD) is a popular algorithm to train deep learning models with provable guarantees on the privacy of the training data. In the last decad…
cs.LG2024★ 1 cited
Average gradient outer product as a mechanism for deep neural collapse
Daniel Beaglehole, Peter Súkeník, Marco Mondelli +1
Deep Neural Collapse (DNC) refers to the surprisingly rigid structure of the data representations in the final layers of Deep Neural Networks (DNNs). Though the phenomenon has been…
stat.ML2024
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
Simone Bombari, Marco Mondelli
Understanding the reasons behind the exceptional success of transformers requires a better analysis of why attention layers are suitable for NLP tasks. In particular, such tasks re…