Ricci Curvature and the Manifold Learning Problem
Preprint
Abstract
Consider a sample of $n$ points taken i.i.d from a submanifold $\Sigma$ of Euclidean space. We show that there is a way to estimate the Ricci curvature of $\Sigma$ with respect to the induced metric from the sample. Our method is grounded in the notions of Carr\'e du Champ for diffusion semi-groups, the theory of Empirical processes and local Principal Component Analysis.
Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Characterizing complex networks with Forman-Ricci curvature and associated geometric flowsJournal of Complex Networks, 2017
- Spectral convergence of the connection Laplacian from random samplesInformation and Inference: A Journal of the IMA, 2016
- Forman curvature for complex networksJournal of Statistical Mechanics: Theory and Experiment, 2016
- Topological pattern recognition for point cloud dataActa Numerica, 2014
- Novel high intrinsic dimensionality estimatorsMachine Learning, 2012
- Vector diffusion maps and the connection LaplacianCommunications on Pure and Applied Mathematics, 2012
- Towards a theoretical foundation for Laplacian-based manifold methodsJournal of Computer and System Sciences, 2008
- Bochner's Method for Cell Complexes and Combinatorial Ricci CurvatureDiscrete & Computational Geometry, 2003
- Intrinsic dimensionality estimation with optimally topology preserving mapsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Absolute Continuity of Markov Processes and GeneratorsNagoya Mathematical Journal, 1969