Wasserstein Bounds for Ambient and Latent Smoothing on Data Manifolds
Abstract
Smoothing empirical data can fill gaps between observations, while noise in the surrounding space can move mass away from the manifold supporting the data. We derive Wasserstein error bounds for ambient Gaussian smoothing and for smoothing through an encoder--decoder representation. For a compact connected smooth manifold without boundary and a smooth positive target density, established heat-flow and entropy estimates imply that sufficiently small intrinsic heat smoothing improves the squared intrinsic Wasserstein error. Coupling this estimate with ambient noise yields a bound whose quadratic term includes ambient dimension and a curvature correction. Our main latent bound tracks reconstruction error, tangential distortion, and the decoder's response to orthogonal latent noise. Its quadratic surrogate gives bandwidth rules and explicit conditions under which the latent upper-bound surrogate is smaller than the ambient one. These surrogate comparisons do not assert an ordering of the exact Wasserstein errors. Synthetic experiments examine the predicted scaling and latent geometry on spheres and a product of spheres.
Related
- Smoothing topological isotopy of surfaces in 4-manifolds with a boundary geometric dual
- Fractional porous medium equation on manifolds with nonnegative Ricci curvature: existence of solutions and smoothing effects via potential methods
- Error Bounds and a Smoothing Penalty Method for Binary Orthogonal Optimization
- Ambient and Poincaré metrics for CR $3$-manifolds associated with the self-dual Einstein ACH metric
- Asymptotics and finite sample bounds for prediction and smoothing in Wright-Fisher hidden Markov models
BibTeX
@misc{lee2026wasserstein,
title = {{Wasserstein Bounds for Ambient and Latent Smoothing on Data Manifolds}},
author = {Wonjun Lee and Wenyan Luo},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.33629},
eprint = {2609.33629},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.33629},
}
RIS
TY - UNPB
TI - Wasserstein Bounds for Ambient and Latent Smoothing on Data Manifolds
AU - Wonjun Lee
AU - Wenyan Luo
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2609.33629
UR - https://arxiv.org/abs/2609.33629
AB - Smoothing empirical data can fill gaps between observations, while noise in the surrounding space can move mass away from the manifold supporting the data. We derive Wasserstein error bounds for ambient Gaussian smoothing and for smoothing through an encoder--decoder representation. For a compact connected smooth manifold without boundary and a smooth positive target density, established heat-flow and entropy estimates imply that sufficiently small intrinsic heat smoothing improves the squared intrinsic Wasserstein error. Coupling this estimate with ambient noise yields a bound whose quadratic term includes ambient dimension and a curvature correction. Our main latent bound tracks reconstruction error, tangential distortion, and the decoder's response to orthogonal latent noise. Its quadratic surrogate gives bandwidth rules and explicit conditions under which the latent upper-bound surrogate is smaller than the ambient one. These surrogate comparisons do not assert an ordering of the exact Wasserstein errors. Synthetic experiments examine the predicted scaling and latent geometry on spheres and a product of spheres.
ER -