English

The Singular Values of Convolutional Layers

Machine Learning 2019-03-07 v2 Artificial Intelligence Machine Learning

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\%.

Keywords

Cite

@article{arxiv.1805.10408,
  title  = {The Singular Values of Convolutional Layers},
  author = {Hanie Sedghi and Vineet Gupta and Philip M. Long},
  journal= {arXiv preprint arXiv:1805.10408},
  year   = {2019}
}

Comments

Published as a conference paper at ICLR 2019

R2 v1 2026-06-23T02:09:02.511Z