Riemannian Regression
Abstract
Classical linear regression assumes that the relevant geometry of the predictor space is Euclidean and that all centered observations contribute to the least-squares fit in the same geometric scale. This paper proposes \emph{Riemannian Regression}, a regression framework in which the usual vector differences are replaced by locally weighted differences induced by a data-dependent similarity structure. We introduce a generalized framework, termed {\em Riemannian Regression}, extending classic regression to any data endowed with a local distance structure. By equipping data tables with local metrics, we adapt regression model to incorporate manifold geometry. Given a similarity matrix S=(Sij), obtained from UMAP, ISOMAP, or DBSCAN \cite{mcinnes,isomap,dbscan}, we define the dissimilarity coefficient ρij=1−Sij and the induced subtraction $ x_i\ominus x_j=ρ_{ij}(x_i-x_j). $ A Riemannian center g=xλ is selected as a discrete Fréchet mean, and regression is performed on the Riemannian-centered variables XR=W Xc,λ and yR=W yc,λ, where W=diag(ρ1λ,…,ρnλ). The resulting estimator has the weighted least-squares form $ \widehatβ_R=(X_{c,λ}^{t}W^2X_{c,λ})^{-1}X_{c,λ}^{t}W^2y_{c,λ}. $ The proposed approach preserves the linear form of the regression model while changing the geometry of the fit. The paper develops three ways to construct the local metric: UMAP-based fuzzy similarities, ISOMAP-based normalized geodesic distances, and DBSCAN-based density similarities. Simulated examples and the Abalone data set illustrate how Riemannian Regression can reduce the influence of locally anomalous observations and adapt to regions with different local densities.
Related
- Kernel Density Regression Estimation with Covariates on Riemannian Manifolds
- Riemannian Simultaneous Inference for Tangent Vector Field Regression
- Spline interpolation on compact riemannian manifolds
- Calderón problem for fractional Schrödinger operators on closed Riemannian manifolds
- Solving the Yamabe problem by an iterative method on a small Riemannian domain
BibTeX
@misc{rodriguez2026riemannian,
title = {{Riemannian Regression}},
author = {Oldemar Rodríguez},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.40242},
eprint = {2609.40242},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.40242},
}
RIS
TY - UNPB
TI - Riemannian Regression
AU - Oldemar Rodríguez
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.40242
UR - https://arxiv.org/abs/2609.40242
AB - Classical linear regression assumes that the relevant geometry of the predictor space is Euclidean and that all centered observations contribute to the least-squares fit in the same geometric scale. This paper proposes \emph{Riemannian Regression}, a regression framework in which the usual vector differences are replaced by locally weighted differences induced by a data-dependent similarity structure. We introduce a generalized framework, termed {\em Riemannian Regression}, extending classic regression to any data endowed with a local distance structure. By equipping data tables with local metrics, we adapt regression model to incorporate manifold geometry. Given a similarity matrix S=(S_ij), obtained from UMAP, ISOMAP, or DBSCAN \cite{mcinnes,isomap,dbscan}, we define the dissimilarity coefficient ρ_ij=1−S_ij and the induced subtraction $ x_i\ominus x_j=ρ_{ij}(x_i-x_j). $ A Riemannian center g=x_λ is selected as a discrete Fréchet mean, and regression is performed on the Riemannian-centered variables X_R=W X_c,λ and y_R=W y_c,λ, where W=diag(ρ_1λ,…,ρ_nλ). The resulting estimator has the weighted least-squares form $ \widehatβ_R=(X_{c,λ}^{t}W^2X_{c,λ})^{-1}X_{c,λ}^{t}W^2y_{c,λ}. $ The proposed approach preserves the linear form of the regression model while changing the geometry of the fit. The paper develops three ways to construct the local metric: UMAP-based fuzzy similarities, ISOMAP-based normalized geodesic distances, and DBSCAN-based density similarities. Simulated examples and the Abalone data set illustrate how Riemannian Regression can reduce the influence of locally anomalous observations and adapt to regions with different local densities.
ER -