Identifiability and Consistent Recovery for the Unnormalized Graph Laplace Operators
Abstract
We study whether an unnormalized graph Laplace operator can determine both the geometry of a manifold and its sampling density. On a fixed compact smooth manifold without boundary, we use a known positive, continuous, strictly decreasing radial kernel at a fixed positive bandwidth. For positive sampling densities, the operator built from geodesic distances determines the Riemannian metric and identifies the density up to equality almost everywhere. When the metric is induced by a Euclidean embedding, the operator built from ambient distances also determines the embedding up to rotations, reflections and translations, and the density. On compact parameter classes with positive continuous densities, minimizing the distance between empirical and popula- tion operators gives estimates that converge to the true parameters under independent, identically distributed sampling. This recovery result assumes that the empirical operator can be evaluated at arbitrary points of the manifold.
Related
- A unified approach for estimation of unnormalized models via Stein operators
- Consistent Order Selection under Non-Identifiability and Dependence
- Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds
- Laplace and Dolbeault operators on Sasakian manifolds
- Fractional Laplace Neural Operators: Exact Architectures, an Expressivity Frontier at Criticality, and Certified Stability for Memory-Driven Network Dynamics
BibTeX
@misc{pal2026identifiability,
title = {{Identifiability and Consistent Recovery for the Unnormalized Graph Laplace Operators}},
author = {Susovan Pal},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.17032},
eprint = {2610.17032},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.17032},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Identifiability and Consistent Recovery for the Unnormalized Graph Laplace Operators
AU - Susovan Pal
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.17032
UR - https://arxiv.org/abs/2610.17032
AB - We study whether an unnormalized graph Laplace operator can determine both the geometry of a manifold and its sampling density. On a fixed compact smooth manifold without boundary, we use a known positive, continuous, strictly decreasing radial kernel at a fixed positive bandwidth. For positive sampling densities, the operator built from geodesic distances determines the Riemannian metric and identifies the density up to equality almost everywhere. When the metric is induced by a Euclidean embedding, the operator built from ambient distances also determines the embedding up to rotations, reflections and translations, and the density. On compact parameter classes with positive continuous densities, minimizing the distance between empirical and popula- tion operators gives estimates that converge to the true parameters under independent, identically distributed sampling. This recovery result assumes that the empirical operator can be evaluated at arbitrary points of the manifold.
ER -