arXiv cs.LG
· Papers
Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks
arXiv:2605.00366v4 Announce Type: replace-cross Abstract: High-capacity associative memories based on Kernel Logistic Regression (KLR) exhibit strong storage capabilities, but the dynamical and geometric mechanisms underlying their stability remain poorly understood. This paper investigates the global geometry of attra