Analysis of the expected L₂ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization

Abstract

Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L_2$ risk are universally consistent and achieve good rates of convergence. In this paper, we show that the regularization term is not necessary to obtain similar results. In the case of a suitably chosen initialization of the network, a suitable number of gradient descent steps, and a suitable step size we show that an estimate without a regularization term is universally consistent for bounded predictor variables. Additionally, we show that if the regression function is Hölder smooth with Hölder exponent $1/2 \leq p \leq 1$, the $L_2$ error converges to zero with a convergence rate of approximately $n^{-1/(1+d)}$. Furthermore, in case of an interaction model, where the regression function consists of a sum of Hölder smooth functions with $d^*$ components, a rate of convergence is derived which does not depend on the input dimension $d$.