6 papers
Path-conditioned training: a principled way to rescale ReLU neural networks
Arthur Lebeurrier, Titouan Vayer, Rémi Gribonval
Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters. While two properly rescal…
Non-Vacuous Generalization Bounds: Can Rescaling Invariances Help?
Damien Rouchouse, Antoine Gonon, Rémi Gribonval +1
A central challenge in understanding generalization is to obtain non-vacuous guarantees that go beyond worst-case complexity over data or weight space. Among existing approaches, P…
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,…
PASCO (PArallel Structured COarsening): an overlay to speed up graph clustering algorithms
Etienne Lasalle, Rémi Vaudaine, Titouan Vayer +4
Clustering the nodes of a graph is a cornerstone of graph analysis and has been extensively studied. However, some popular methods are not suitable for very large graphs: e.g., spe…
Butterfly factorization with error guarantees
Quoc-Tung Le, Léon Zheng, Elisa Riccietti +1
In this paper, we investigate the butterfly factorization problem, i.e., the problem of approximating a matrix by a product of sparse and structured factors. We propose a new forma…
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…