AI RESEARCH
ECLipsE-Gen-Local: Efficient Compositional Local Lipschitz Estimates for Deep Neural Networks
arXiv CS.LG
•
ArXi:2510.05261v2 Announce Type: replace The Lipschitz constant is a key measure for certifying the robustness of neural networks to input perturbations. However, computing the exact constant is NP-hard, and standard approaches to estimate the Lipschitz constant involve solving a large matrix semidefinite program (SDP) that scales poorly with network size. Further, there is a potential to efficiently leverage local information on the input region to provide tighter Lipschitz estimates.