Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Machine Learning
2022-06-29 v2 Optimization and Control
Machine Learning
Abstract
The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently address the role of depth in deep learning. In this work, we present the first trainability guarantee of infinitely deep but narrow neural networks. We study the infinite-depth limit of a multilayer perceptron (MLP) with a specific initialization and establish a trainability guarantee using the NTK theory. We then extend the analysis to an infinitely deep convolutional neural network (CNN) and perform brief experiments.
Keywords
Cite
@article{arxiv.2202.02981,
title = {Neural Tangent Kernel Analysis of Deep Narrow Neural Networks},
author = {Jongmin Lee and Joo Young Choi and Ernest K. Ryu and Albert No},
journal= {arXiv preprint arXiv:2202.02981},
year = {2022}
}