3 citations · 3 across the 9 of their papers we have counts for
3 papers · 1 filter
A path-norm toolkit for modern networks: consequences, promises and challenges
Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti +1
This work introduces the first toolkit around path-norms that fully encompasses general DAG ReLU networks with biases, skip connections and any operation based on the extraction of…
Sparsity in neural networks can improve their privacy
Antoine Gonon, Léon Zheng, Clément Lalanne +3
This article measures how sparsity can make neural networks more robust to membership inference attacks. The obtained empirical results show that sparsity improves the privacy of t…
Can sparsity improve the privacy of neural networks?
Antoine Gonon, Léon Zheng, Clément Lalanne +3
Sparse neural networks are mainly motivated by ressource efficiency since they use fewer parameters than their dense counterparts but still reach comparable accuracies. This articl…