Implicit Bias of Gradient Descent on Linear Convolutional Networks
Machine Learning
2019-01-14 v2 Machine Learning
Abstract
We show that gradient descent on full-width linear convolutional networks of depth converges to a linear predictor related to the bridge penalty in the frequency domain. This is in contrast to linearly fully connected networks, where gradient descent converges to the hard margin linear support vector machine solution, regardless of depth.
Cite
@article{arxiv.1806.00468,
title = {Implicit Bias of Gradient Descent on Linear Convolutional Networks},
author = {Suriya Gunasekar and Jason Lee and Daniel Soudry and Nathan Srebro},
journal= {arXiv preprint arXiv:1806.00468},
year = {2019}
}