Fitting an immersed submanifold to data via Sussmann’s orbit theorem

This paper describes an approach for fitting an immersed submanifold of a finite-dimensional Euclidean space to random samples. The reconstruction mapping from the ambient space to the desired submanifold is implemented as a composition of an encoder that maps each point to a tuple of (positive or n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mathematics of control, signals, and systems Jg. 37; H. 3; S. 479 - 506
Hauptverfasser: Hanson, Joshua, Raginsky, Maxim
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.09.2025
Springer Nature B.V
Schlagworte:
Coders
Communications Engineering
Composition
Control
Euclidean geometry
Fields (mathematics)
Image reconstruction
Machine learning
Manifolds (mathematics)
Mathematics
Mathematics and Statistics
Mechatronics
Networks
Original Article
Robotics
Systems Theory
Theorems
Geometric control
Manifold learning
Neural nets
Encoder-decoder architectures
Unsupervised learning
ISSN:0932-4194, 1435-568X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper describes an approach for fitting an immersed submanifold of a finite-dimensional Euclidean space to random samples. The reconstruction mapping from the ambient space to the desired submanifold is implemented as a composition of an encoder that maps each point to a tuple of (positive or negative) times and a decoder given by a composition of flows along finitely many vector fields starting from a fixed initial point. The encoder supplies the times for the flows. The encoder–decoder map is obtained by empirical risk minimization, and a high-probability bound is given on the excess risk relative to the minimum expected reconstruction error over a given class of encoder–decoder maps. The proposed approach makes fundamental use of Sussmann’s orbit theorem, which guarantees that the image of the reconstruction map is indeed contained in an immersed submanifold.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0932-4194
1435-568X
DOI:10.1007/s00498-025-00410-2