Estimating the Cheeger constant using machine learning
Combinatorics
2020-05-13 v1 Machine Learning
Abstract
In this paper, we use machine learning to show that the Cheeger constant of a connected regular graph has a predominant linear dependence on the largest two eigenvalues of the graph spectrum. We also show that a trained deep neural network on graphs of smaller sizes can be used as an effective estimator in estimating the Cheeger constant of larger graphs.
Keywords
Cite
@article{arxiv.2005.05812,
title = {Estimating the Cheeger constant using machine learning},
author = {Ambar Jain and Shivam Pal and Kashyap Rajeevsarathy},
journal= {arXiv preprint arXiv:2005.05812},
year = {2020}
}
Comments
8 figures, 1 table