What's Hidden in a Randomly Weighted Neural Network?
Vivek Ramanujan, Mitchell Wortsman, Aniruddha Kembhavi, Ali Farhadi, Mohammad Rastegari
Abstract
Training a neural network is synonymous with learning the values of the weights. By contrast, we demonstrate that randomly weighted neural networks contain subnetworks which achieve impressive performance without ever training the weight values. Hidden in a randomly weighted Wide ResNet-50 is a subnetwork (with random weights) that is smaller than, but matches the performance of a ResNet-34 trained on ImageNet. Not only do these "untrained subnetworks" exist, but we provide an algorithm to effectively find them. We empirically show that as randomly weighted neural networks with fixed weights grow wider and deeper, an "untrained subnetwork" approaches a network with learned weights in accuracy.
BibTeX
@inproceedings{cvpr2020_whatshiddeninara,
title = {What's Hidden in a Randomly Weighted Neural Network?},
author = {Vivek Ramanujan and Mitchell Wortsman and Aniruddha Kembhavi and Ali Farhadi and Mohammad Rastegari},
booktitle = {CVPR 2020},
year = {2020}
}