AI RESEARCH

State-Space NTK Collapse Near Bifurcations

arXiv CS.LG

ArXi:2605.12763v1 Announce Type: new Rich feature learning in tasks that unfold over time often requires the model to pass through bifurcations, constituting qualitative changes in the underlying model dynamics. We develop a local theory of gradient descent near these transitions through the empirical state-space neural tangent kernel (s