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

Source: [Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent](<https://www.sota2.com/research/paper/68fa73321e209131cea5b10f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:44:18.752Z

Authors: Michael Kohler, Adam Krzyzak, Benjamin Walter

Published: 2024-05-13T10:26:28.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2405.07619>)

[PDF](<https://arxiv.org/pdf/2405.07619.pdf>)