Graph Laplacians, Riemannian Manifolds and their Machine-Learning
arXiv:2006.16619
Abstract
Graph Laplacians as well as related spectral inequalities and (co-)homology provide a foray into discrete analogues of Riemannian manifolds, providing a rich interplay between combinatorics, geometry and theoretical physics. We apply some of the latest techniques in data science such as supervised and unsupervised machine-learning and topological data analysis to the Wolfram database of some 8000 finite graphs in light of studying these correspondences. Encouragingly, we find that neural classifiers, regressors and networks can perform, with high efficiently and accuracy, a multitude of tasks ranging from recognizing graph Ricci-flatness, to predicting the spectral gap, to detecting the presence of Hamiltonian cycles, etc.
47+1 pages, 30 figures
References in corpus (10)
- Machine Learning of Calabi-Yau Volumes
- Branes with Brains: Exploring String Vacua with Deep Reinforcement Learning
- Deep Learning for Symbolic Mathematics
- Machine Learning meets Number Theory: The Data Science of Birch-Swinnerton-Dyer
- Lectures on the Calabi-Yau Landscape
- Machine Learning Etudes in Conformal Field Theories
- Graphs with large girth and nonnegative curvature dimension condition
- A brief review on geometry and spectrum of graphs
- Li-Yau inequality for unbounded Laplacian on graphs
- Ricci-flat graphs with girth at least five