Article,

Over-parametrized deep neural networks do not generalize well

, and .
(2019)cite arxiv:1912.03925.

Abstract

Recently it was shown in several papers that backpropagation is able to find the global minimum of the empirical risk on the training data using over-parametrized deep neural networks. In this paper a similar result is shown for deep neural networks with the sigmoidal squasher activation function in a regression setting, and a lower bound is presented which proves that these networks do not generalize well on a new data in the sense that they do not achieve the optimal minimax rate of convergence for estimation of smooth regression functions.

Tags

Users

  • @kirk86

Comments and Reviews