Title |
|---|
 Local Identifiability of Deep ReLU Neural Networks: the TheoryNeural Information Processing Systems (NeurIPS), 2022 |
 Understanding the Generalization Benefit of Normalization Layers:
Sharpness ReductionNeural Information Processing Systems (NeurIPS), 2022 |
 On the Symmetries of Deep Learning Models and their Internal
RepresentationsNeural Information Processing Systems (NeurIPS), 2022 |
 An Embedding of ReLU Networks and an Analysis of their IdentifiabilityConstructive approximation (Constr. Approx.), 2021 Pierre Stock Rémi Gribonval |
 ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning
of Deep Neural NetworksInternational Conference on Machine Learning (ICML), 2021 |
 Understanding Decoupled and Early Weight DecayAAAI Conference on Artificial Intelligence (AAAI), 2020 |
 |
