Lipschitz Certificates for Neural Network Structures Driven by Averaged Activation Operators

Obtaining sharp Lipschitz constants for feed-forward neural networks is essential to assess their robustness in the face of perturbations of their inputs. We derive such constants in the context of...

ML methods Security & robustness Adversarial Robustness in Machine Learning Model Reduction and Neural Networks Machine Learning and ELM

Open-access PDF Source

Paper

Similar papers

Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation OperatorsPatrick L. Combettes, Jean‐Christophe Pesquet2020 · SIAM Journal on Mathematics of Data Science In Library

Local Lipschitz Bounds of Deep Neural NetworksCalypso Herrera, Florian Krach, Josef Teichmann2020 · arXiv (Cornell University) · 9 citations In Library

Lipschitz Constants of Hybrid Zonotope Representations of Feedforward Neural NetworksJustin Chen, Jonah J. Glunt, Justin P. Koeln et al.2025 · American Control Conference · 0 citations In Library

Lipschitz constant estimation for general neural network architectures using control toolsPatricia Pauli, Dennis Gramlich, Frank Allgöwer2024 · arXiv (Cornell University) · 10 citations In Library

Lipschitz Bound Analysis of Neural NetworksSarosij Bose2022 · 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT) In Library

Lipschitz Bound Analysis of Neural NetworksSarosij Bose2022 · arXiv (Cornell University) · 0 citations In Library

ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural NetworksYuezhu Xu, S. Sivaranjani2024 · Neural Information Processing Systems · 18 citations In Library

The Lipschitz Constant of Self-AttentionHyunjik Kim, G. Papamakarios, A. Mnih2020 · International Conference on Machine Learning · 231 citations In Library

An Analysis of the Expressiveness of Deep Neural Network Architectures Based on Their Lipschitz ConstantsSiqi Zhou, Angela P. Schoellig2019 · arXiv.org · 13 citations In Library

The Lipschitz Constant of Self-AttentionHyunjik Kim, George Papamakarios, Andriy Mnih2021 · International Conference on Machine Learning In Library

Source of record

OpenAlex

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal