A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations

Antoine Gonon; Nicolas Brisebarre; Elisa Riccietti; Remi Gribonval

2025 ICML ICML 2025

A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti, Remi Gribonval

Topics

Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Application Areas > Efficient Computing Deep Learning > Architectures > Neural Networks

Keywords

relu network lipschitz bound path metric neuron-wise rescaling pruning criterion resnet-18

Download PDF