The Singular Values of Convolutional Layers
Hanie Sedghi · Vineet Gupta · Phil Long
2019 Poster
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%.
Chat is not available.
Successful Page Load