Work

The Singular Values of Convolutional Layers

Year: 2018
Type: preprint
Abstract: We characterize the singular values of the linear transformation associated with a standard 2D multi-channel convolutional layer, enabling their efficient computation. This characterization also leads to an algorithm for projecting a convolutional layer onto an operator-norm ball. We show that this is an effective regularizer; for example, it improves the test error of a deep residual network using batch normalization on CIFAR-10 from 6.2\% to 5.3\%.
Language: English
Open Access status: green
OpenAlex ID: W2803968356
Cites: 20
Cited by: 184
Related to: 9