Non-convergence of stochastic gradient descent in the training of deep neural networks

https://doi.org/10.1016/j.jco.2020.101540Get rights and content
Under a Creative Commons license
open access

Abstract

Deep neural networks have successfully been trained in various application areas with stochastic gradient descent. However, there exists no rigorous mathematical explanation why this works so well. The training of neural networks with stochastic gradient descent has four different discretization parameters: (i) the network architecture; (ii) the amount of training data; (iii) the number of gradient steps; and (iv) the number of randomly initialized gradient trajectories. While it can be shown that the approximation error converges to zero if all four parameters are sent to infinity in the right order, we demonstrate in this paper that stochastic gradient descent fails to converge for ReLU networks if their depth is much larger than their width and the number of random initializations does not increase to infinity fast enough.

Keywords

Machine learning
Deep neural networks
Stochastic gradient descend
Empirical risk minimization
Non-convergence

Cited by (0)

Communicated by E. Novak.