AI RESEARCH
Collective Kernel EFT for Pre-activation ResNets
arXiv CS.LG
•
ArXi:2604.15742v1 Announce Type: new In finite-width deep neural networks, the empirical kernel $G$ evolves stochastically across layers. We develop a collective kernel effective field theory (EFT) for pre-activation ResNets based on a $G$-only closure hierarchy and diagnose its finite validity window. Exploiting the exact conditional Gaussianity of residual increments, we derive an exact stochastic recursion for $G