AI RESEARCH
Scaling of Gaussian Kolmogorov--Arnold Networks
arXiv CS.AI
•
ArXi:2604.21174v1 Announce Type: cross The Gaussian scale parameter \(\epsilon\) is central to the behavior of Gaussian Kolmogoro--Arnold Networks (KANs), yet its role in deep edge-based architectures has not been studied systematically. In this paper, we investigate how \(\epsilon\) affects Gaussian KANs through first-layer feature geometry, conditioning, and approximation behavior.