Quantitative CLTs in Deep Neural Networks

Authors Stefano Favaro, Boris Hanin, Domenico Marinucci, Ivan Nourdin, Giovanni Peccati

Publication date 12 July 2023

Abstract: We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant

n

. Under mild assumptions on the non-linearity, we obtain quantitative bounds on normal approximations valid at large but finite

n

and any fixed network depth. Our theorems show, both for the finite-dimensional distributions and the entire process, that the distance between a random fully connected network (and its derivatives) to the corresponding infinite width Gaussian process scales like

n^{- g a m m a}

for

g a m m a > 0,

with the exponent depending on the metric used to measure discrepancy. Our bounds are stronger in terms of their dependence on network width than any previously available in the literature.

This page was built for publication: Quantitative CLTs in Deep Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6443485)