Local Lipschitz Constant Computation of ReLU-FNNs: Upper Bound Computation with Exactness Verification

arXiv:2310.11104v2 Announce Type: replace-cross
Abstract: This paper is concerned with the computation of the local Lipschitz constant of feedforward neural networks (FNNs) with activation functions being rectified linear units (ReLUs). The local Lipschitz constant of an FNN for a target input is a reasonable measure for its quantitative evaluation of the reliability. By following a standard procedure using multipliers that capture the behavior of ReLUs,we first reduce the upper bound computation problem of the local Lipschitz constant into a semidefinite …

abstract arxiv computation cs.lg functions linear math.oc networks neural networks paper quantitative relu type units verification