Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent

Michael Kohler, Adam Krzyzak, Benjamin Walter
5/13/2024
stat.MLcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Image classification based on over-parametrized convolutional neural networks with a global average-pooling layer is considered. The weights of the network are learned by gradient descent. A bound on the rate of convergence of the difference between the misclassification risk of the newly introduced convolutional neural network estimate and the minimal possible value is derived.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Convergence of gradient flow for learning convolutional neural networks

84% match2026

On Excess Risk Convergence Rates of Neural Network Classifiers

84% match2023

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective

80% match2026

Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search

80% match2024

Fast Convergence in Learning Two-Layer Neural Networks with Separable Data

80% match2023

Universal Training of Neural Networks to Achieve Bayes Optimal Classification Accuracy

80% match2025

Cite this paper

@article{kohler2024analysis,
  title  = {Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent},
  author = {Michael Kohler and Adam Krzyzak and Benjamin Walter},
  year   = {2024},
  eprint = {2405.07619},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.07619v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.07619.svg)](https://codeofpaper.com/paper/2405.07619)

Discussion