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.
Impact Factor
Scopus SNIP
Web of Science Times Cited
Scopus Cited By
Altmetric
0
1
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern
PublikationstypArtikel: Konferenzbeitrag
Dokumenttyp
Typ der Hochschulschrift
Herausgeber
Schlagwörter
Keywords plus
Spracheenglisch
Veröffentlichungsjahr2022
Prepublished im Jahr 0
HGF-Berichtsjahr2022
ISSN (print) / ISBN1049-5258
e-ISSN
ISBN
Bandtitel
KonferenztitelAdvances in Neural Information Processing Systems