ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2311.14609
21
2

Analysis of the expected L2L_2L2​ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization

24 November 2023
Selina Drews
Michael Kohler
ArXivPDFHTML
Abstract

Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical L2L_2L2​ 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 H\"older smooth with H\"older exponent 1/2≤p≤11/2 \leq p \leq 11/2≤p≤1, the L2L_2L2​ error converges to zero with a convergence rate of approximately n−1/(1+d)n^{-1/(1+d)}n−1/(1+d). Furthermore, in case of an interaction model, where the regression function consists of a sum of H\"older smooth functions with d∗d^*d∗ components, a rate of convergence is derived which does not depend on the input dimension ddd.

View on arXiv
Comments on this paper