Full error analysis for the training of deep neural networks

TL;DR

This paper provides a comprehensive error analysis for deep neural network training, decomposing the total error into approximation, generalization, and optimization errors, and establishing convergence with a slow, dimension-dependent speed.

Contribution

It introduces a full error decomposition framework for deep learning algorithms, combining the three main error sources into a unified convergence analysis.

Findings

Estimates each error component separately

Combines errors to analyze overall convergence

Shows convergence speed is slow and dimension-dependent

Abstract

Deep learning algorithms have been applied very successfully in recent years to a range of problems out of reach for classical solution paradigms. Nevertheless, there is no completely rigorous mathematical error and convergence analysis which explains the success of deep learning algorithms. The error of a deep learning algorithm can in many situations be decomposed into three parts, the approximation error, the generalization error, and the optimization error. In this work we estimate for a certain deep learning algorithm each of these three errors and combine these three error estimates to obtain an overall error analysis for the deep learning algorithm under consideration. In particular, we thereby establish convergence with a suitable convergence speed for the overall error of the deep learning algorithm under consideration. Our convergence speed analysis is far from optimal and the convergence speed that we establish is rather slow, increases exponentially in the dimensions, and, in particular, suffers from the curse of dimensionality. The main contribution of this work is, instead, to provide a full error analysis (i) which covers each of the three different sources of errors usually emerging in deep learning algorithms and (ii) which merges these three sources of errors into one overall error estimate for the considered deep learning algorithm.