Download this article
 Download this article For screen
For printing
Recent Issues
Volume 7, Issue 3
Volume 7, Issue 2
Volume 7, Issue 1
Volume 6, Issue 4
Volume 6, Issue 3
Volume 6, Issue 2
Volume 6, Issue 1
Volume 5, Issue 4
Volume 5, Issue 3
Volume 5, Issue 2
Volume 5, Issue 1
Volume 4, Issue 4
Volume 4, Issue 3
Volume 4, Issue 2
Volume 4, Issue 1
Volume 3, Issue 4
Volume 3, Issue 3
Volume 3, Issue 2
Volume 3, Issue 1
Volume 2, Issue 4
Volume 2, Issue 3
Volume 2, Issue 2
Volume 2, Issue 1
Volume 1, Issue 4
Volume 1, Issue 3
Volume 1, Issue 2
Volume 1, Issue 1
The Journal
About the journal
Ethics and policies
Peer-review process
 
Submission guidelines
Submission form
Editorial board
 
Subscriptions
 
ISSN 2578-5885 (online)
ISSN 2578-5893 (print)
Author Index
To Appear
 
Other MSP Journals
Convergence of Hessian estimator from random samples on a manifold with boundary

Chih-Wei Chen and Hau-Tieng Wu

Vol. 7 (2025), No. 3, 807–864
Abstract

A common method for estimating the Hessian operator from random samples on a low-dimensional manifold involves locally fitting a quadratic polynomial. Although widely used, it is unclear if this estimator introduces bias, especially in complex manifolds with boundaries and nonuniform sampling. Rigorous theoretical guarantees of its asymptotic behavior have been lacking. We show that, under mild conditions, this estimator asymptotically converges to the Hessian operator, with nonuniform sampling and curvature effects proving negligible, even near boundaries. Our analysis framework simplifies the intensive computations required for direct analysis.

Keywords
manifold learning, Hessian operator
Mathematical Subject Classification
Primary: 62-08, 68Q87, 68W40
Milestones
Received: 12 July 2024
Revised: 7 April 2025
Accepted: 15 July 2025
Published: 4 September 2025
Authors
Chih-Wei Chen
Department of Applied Mathematics
National Sun Yat-sen University
Kaohsiung
Taiwan
Hau-Tieng Wu
Courant Institute of Mathematical Sciences
New York University
New York, NY
United States