Collective Kernel EFT for Pre-activation ResNets

Abstract

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. Applying Gaussian approximations systematically yields a continuous-depth ODE system for the mean kernel K0, the kernel covariance V4, and the 1/n mean correction K1,EFT, which emerges diagrammatically as a one-loop tadpole correction. Numerically, K0 remains accurate at all depths. However, the V4 equation residual accumulates to an O(1) error at finite time, primarily driven by approximation errors in the G-only transport term. Furthermore, K1,EFT fails due to the breakdown of the source closure, which exhibits a systematic mismatch even at initialization. These findings highlight the limitations of G-only state-space reduction and suggest extending the state space to incorporate the sigma-kernel.

0

Turn this paper into a lesson

ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.

Discussion (0)

Sign in to join the discussion.

Loading comments…