3 papers
cs.LG2024
A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations
Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti +1
Robustness with respect to weight perturbations underpins guarantees for generalization, pruning and quantization. Existing guarantees rely on Lipschitz bounds in parameter space,…
stat.ML2023
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…
cs.IT2022
Approximation speed of quantized vs. unquantized ReLU neural networks and beyond
Antoine Gonon, Nicolas Brisebarre, Rémi Gribonval +1
We deal with two complementary questions about approximation properties of ReLU networks. First, we study how the uniform quantization of ReLU networks with real-valued weights imp…