Universality in Deep Neural Networks: An approach via the Lindeberg exchange principle
Filippo Giovagnini, Sotirios Kotitsas, Marco Romito
math.PR cs.LG stat.ML
Abstract
We consider the infinite-width limit of a fully connected deep neural network with general weights, and we prove quantitative general bounds on the $2$-Wasserstein distance between the network and its infinite-width Gaussian limit, under appropriate regularity assumptions on the activation function. Our main tool is a Lindeberg principle for Deep Neural Networks, which we use to successively replace the weights on each layer by Gaussian random variables.
Topics
Classified with taxonomy v2 on Wed, 2 Sept 2026.