Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning

DOI10.1007/S00526-024-02721-9MaRDI QIDQ6493699zbMATH OpenFDO

Authors Leon Bungert, Kerrek Stinson

Publication date 29 April 2024

Published in Calculus of Variations and Partial Differential Equations (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S00526-024-02721-9

Mathematics Subject Classification ID

Length, area, volume, other geometric measure theory (28A75) Methods involving semicontinuity and convergence; relaxation (49J45) Geometric probability and stochastic geometry (60D05) Graph theory (including graph drawing) in computer science (68R10)

Recommendations

• The geometry of adversarial training in binary classification
• Gamma-convergence of nonlocal perimeter functionals
• \Gamma-Convergence of Discrete Functionals with Nonconvex Perturbation for Image Classification
• On the asymptotic behaviour of nonlocal perimeters
• Clustering of big data: consistency of a nonlocal Ginzburg-Landau type model

Cited in

(7)

• The geometry of adversarial training in binary classification
• A mean curvature flow arising in adversarial training
• Nonlocal perimeters and variations: extremality and decomposability for finite and infinite horizons
• Adversarial flows: a gradient flow characterization of adversarial attacks
• Uniform convergence of adversarially robust classifiers
• An elliptic approximation for phase separation in a fractured material
• On De Giorgi's conjecture of nonlocal approximations for free-discontinuity problems: the symmetric gradient case

This page was built for publication: Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6493699)