DeepAI AI Chat
Log In Sign Up

Diffusion Curvature for Estimating Local Curvature in High Dimensional Data

by   Dhananjay Bhaskar, et al.
Yale University

We introduce a new intrinsic measure of local curvature on point-cloud data called diffusion curvature. Our measure uses the framework of diffusion maps, including the data diffusion operator, to structure point cloud data and define local curvature based on the laziness of a random walk starting at a point or region of the data. We show that this laziness directly relates to volume comparison results from Riemannian geometry. We then extend this scalar curvature notion to an entire quadratic form using neural network estimations based on the diffusion map of point-cloud data. We show applications of both estimations on toy data, single-cell data, and on estimating local Hessian matrices of neural network loss landscapes.


page 1

page 2

page 3

page 4


Efficient Curvature Estimation for Oriented Point Clouds

There is an immense literature focused on estimating the curvature of an...

Curvature Regularized Surface Reconstruction from Point Cloud

We propose a variational functional and fast algorithms to reconstruct i...

Visualizing high-dimensional loss landscapes with Hessian directions

Analyzing geometric properties of high-dimensional loss functions, such ...

Robust Estimation of Surface Curvature Information from Point Cloud Data

This paper surveys and evaluates some popular state of the art methods f...

Emergent properties of the local geometry of neural loss landscapes

The local geometry of high dimensional neural network loss landscapes ca...

Self-Sampling for Neural Point Cloud Consolidation

In this paper, we introduce a deep learning technique for consolidating ...

Curvature of Hypergraphs via Multi-Marginal Optimal Transport

We introduce a novel definition of curvature for hypergraphs, a natural ...