Band-limited Training and Inference for Convolutional Neural Networks
Abstract
The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We explore artificially constraining the frequency spectra of these filters and data, called band-limiting, during training. The frequency domain constraints apply to both the feed-forward and back-propagation steps. Experimentally, we observe that Convolutional Neural Networks (CNNs) are resilient to this compression scheme and results suggest that CNNs learn to leverage lower-frequency components. In particular, we found: (1) band-limited training can effectively control the resource usage (GPU and memory); (2) models trained with band-limited layers retain high prediction accuracy; and (3) requires no modification to existing training algorithms or neural network architectures to use unlike other compression schemes.
Cite
@article{arxiv.1911.09287,
title = {Band-limited Training and Inference for Convolutional Neural Networks},
author = {Adam Dziedzic and John Paparrizos and Sanjay Krishnan and Aaron Elmore and Michael Franklin},
journal= {arXiv preprint arXiv:1911.09287},
year = {2019}
}
Comments
Published at International Conference on Machine Learning (ICML)