Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators | Zendy

Patrick L. Combettes | Zendy; JeanChristophe Pesquet | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators

Author(s) -

Patrick L. Combettes,

JeanChristophe Pesquet

Publication year - 2020

Publication title -

siam journal on mathematics of data science

Language(s) - Uncategorized

Resource type - Journals

ISSN - 2577-0187

DOI - 10.1137/19m1272780

Subject(s) - lipschitz continuity , affine transformation , robustness (evolution) , nonlinear system , computer science , scalar (mathematics) , constant (computer programming) , context (archaeology) , mathematics , artificial neural network , topology (electrical circuits) , pure mathematics , artificial intelligence , physics , geometry , combinatorics , paleontology , biochemistry , chemistry , quantum mechanics , biology , gene , programming language

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...

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research