Finite Depth and Width Corrections to the Neural Tangent Kernel

arXiv1909.05989MaRDI QIDQ6325212FDOQ6325212

Publication date: 12 September 2019

Abstract: We prove the precise scaling, at finite depth and width, for the mean and variance of the neural tangent kernel (NTK) in a randomly initialized ReLU network. The standard deviation is exponential in the ratio of network depth to width. Thus, even in the limit of infinite overparameterization, the NTK is not deterministic if depth and width simultaneously tend to infinity. Moreover, we prove that for such deep and wide networks, the NTK has a non-trivial evolution during training by showing that the mean of its first SGD update is also exponential in the ratio of network depth to width. This is sharp contrast to the regime where depth is fixed and network width is very large. Our results suggest that, unlike relatively shallow and wide networks, deep and wide ReLU networks are capable of learning data-dependent features even in the so-called lazy training regime.

This page was built for publication: Finite Depth and Width Corrections to the Neural Tangent Kernel

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6325212)