The global empirical NTK for finite-width networks has a universal Kronecker-core form that makes it structurally low-rank and biases gradient descent toward dominant modes of joint input-hidden activity.
arXiv preprint arXiv:2402.18377 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Bifurcations cause sNTK to reduce to a dominant rank-one channel matching normal forms, collapsing effective rank and funneling gradient descent into critical dynamical directions.