Paper ID: 2405.07619

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

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.

Submitted: May 13, 2024