DeepAI AI Chat
Log In Sign Up

A Convergence Rate for Manifold Neural Networks

by   Joyce Chew, et al.

High-dimensional data arises in numerous applications, and the rapidly developing field of geometric deep learning seeks to develop neural network architectures to analyze such data in non-Euclidean domains, such as graphs and manifolds. Recent work by Z. Wang, L. Ruiz, and A. Ribeiro has introduced a method for constructing manifold neural networks using the spectral decomposition of the Laplace Beltrami operator. Moreover, in this work, the authors provide a numerical scheme for implementing such neural networks when the manifold is unknown and one only has access to finitely many sample points. The authors show that this scheme, which relies upon building a data-driven graph, converges to the continuum limit as the number of sample points tends to infinity. Here, we build upon this result by establishing a rate of convergence that depends on the intrinsic dimension of the manifold but is independent of the ambient dimension. We also discuss how the rate of convergence depends on the depth of the network and the number of filters used in each layer.


page 1

page 2

page 3

page 4


Convolutional Neural Networks on Manifolds: From Graphs and Back

Geometric deep learning has gained much attention in recent years due to...

Geometric Graph Filters and Neural Networks: Limit Properties and Discriminability Trade-offs

This paper studies the relationship between a graph neural network (GNN)...

Convergence of Laplacian Eigenmaps and its Rate for Submanifolds with Singularities

In this paper, we give a spectral approximation result for the Laplacian...

Geometric Scattering on Measure Spaces

The scattering transform is a multilayered, wavelet-based transform init...

Provable approximation properties for deep neural networks

We discuss approximation of functions using deep neural nets. Given a fu...

Non-Parametric Estimation of Manifolds from Noisy Data

A common observation in data-driven applications is that high dimensiona...

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev

Sampling is a fundamental and arguably very important task with numerous...