A mean curvature flow arising in adversarial training
From MaRDI portal
Publication:6652102
DOI10.1016/j.matpur.2024.103625MaRDI QIDQ6652102
Kerrek Stinson, Tim Laux, Leon Bungert
Publication date: 12 December 2024
Published in: Journal de Mathématiques Pures et Appliquées. Neuvième Série (Search for Journal in Brave)
mean curvature flowminimizing movementsadversarial machine learningadversarial trainingmonotone and consistent schemes
Learning and adaptive systems in artificial intelligence (68T05) Methods involving semicontinuity and convergence; relaxation (49J45) Length, area, volume, other geometric measure theory (28A75) Viscosity solutions to PDEs (35D40) Flows related to mean curvature (53E10)
Cites Work
- Implicit time discretization of the mean curvature flow with a discontinuous forcing term
- Implicit time discretization for the mean curvature flow equation
- Minimal barriers for geometric evolutions
- A semi-supervised heat kernel pagerank MBO algorithm for data classification
- An algorithm for mean curvature motion
- Mean curvature, threshold dynamics, and phase field theory on finite graphs
- Lecture Notes on Mean Curvature Flow, Barriers and Singular Perturbations
- An MBO Scheme on Graphs for Classification and Image Processing
- Continuous limits of discrete perimeters
- Curvature-Driven Flows: A Variational Approach
- A fast marching level set method for monotonically advancing fronts.
- Lipschitz Regularity of Graph Laplacians on Random Data Clouds
- APPROXIMATION OF THE ANISOTROPIC MEAN CURVATURE FLOW
- Aspects of Total Variation RegularizedL1Function Approximation
- Diffusion processes in a small time interval
- The geometry of adversarial training in binary classification
- An Analytical and Geometric Perspective on Adversarial Robustness
- Uniform convergence rates for Lipschitz learning on graphs
- Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning
This page was built for publication: A mean curvature flow arising in adversarial training
