SOURCE-LINKED INTELLIGENCE

Kolmogorov--Arnold stability for discontinuous functions

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Here we investigate the stability of the Kolmogorov--Arnold representation theorem (KART) under adversarial reparameterisations of the hidden layer for multivariate discontinuous and unbounded functions. Our results provide a rigorous mathematical foundation for the structural robustness of modern deep learning architectures, such as Kolmogorov--Arnold Networks (KANs), under adversarial configurations.

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-09-07T08:58:43.000Z

First collected: 2026-09-20T20:52:10.320Z. This is not the publication date.