Ricci Curvature and the Manifold Learning Problem

10/13/2014
by   Antonio G. Ache, et al.
0

Consider a sample of n points taken i.i.d from a submanifold Σ of Euclidean space. We show that there is a way to estimate the Ricci curvature of Σ with respect to the induced metric from the sample. Our method is grounded in the notions of Carré du Champ for diffusion semi-groups, the theory of Empirical processes and local Principal Component Analysis.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/18/2021

Curvature of point clouds through principal component analysis

In this article, we study curvature-like feature value of data sets in E...
research
11/11/2015

Principal Autoparallel Analysis: Data Analysis in Weitzenböck Space

The statistical analysis of data lying on a differentiable, locally Eucl...
research
10/14/2015

Curvature-Metric-Free Surface Remeshing via Principle Component Analysis

In this paper, we present a surface remeshing method with high approxima...
research
11/10/2019

Manifold Denoising by Nonlinear Robust Principal Component Analysis

This paper extends robust principal component analysis (RPCA) to nonline...
research
07/06/2020

On the minmax regret for statistical manifolds: the role of curvature

Model complexity plays an essential role in its selection, namely, by ch...
research
01/26/2004

Surface Triangulation -- The Metric Approach

We embark in a program of studying the problem of better approximating s...
research
06/18/2019

Estimating a Manifold from a Tangent Bundle Learner

Manifold hypotheses are typically used for tasks such as dimensionality ...

Please sign up or login with your details

Forgot password? Click here to reset