Learning Normal Coordinates on Riemannian Manifolds with Flow Charts
Abstract
Riemannian manifolds are powerful models for problems with non-Euclidean structure. Recent work in geometric machine learning has focused on training deep neural networks to learn Riemannian metrics from high-dimensional data. However, many geometric algorithms require repeated evaluations of the exponential and logarithmic maps, whose high computational cost restricts the utility of learned Riemannian manifolds in practice. We propose to address this cost by training a conditional invertible neural network, called a flow chart, to approximate normal coordinates around points on a given Riemannian manifold. With this approach, the exponential and logarithmic maps can be approximated by fast Euclidean operations in the model's learned coordinate space. Our main contribution is an efficient loss function for training flow charts that is nonnegative and, under suitable domain assumptions, is zero precisely when the chart is normal. Across sixteen synthetic and data-derived geometries, flow charts are competitive with a specialized neural geodesic interpolator for logarithmic map estimation, while also being able to estimate the exponential map. When pretrained, flow charts provide a median speedup of 60-70x over numerical baselines at comparable logarithmic map estimation error, and their learned coordinates improve the accuracy of a numerical geodesic solver.
Related
- Effect of Measurement Errors on One‐Sided Synthetic‐RZ Control Charts for Monitoring the Ratio of Two Normal Variables
- Riemannian Structures on Quotients in Elastic Diffeology via Q-Charts
- Spline interpolation on compact riemannian manifolds
- Kernel Density Regression Estimation with Covariates on Riemannian Manifolds
- Smoothness estimation for Whittle–Matérn processes on closed Riemannian manifolds
BibTeX
@misc{cunningham2026learning,
title = {{Learning Normal Coordinates on Riemannian Manifolds with Flow Charts}},
author = {Edmond Cunningham},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28302},
eprint = {2610.28302},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28302},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning Normal Coordinates on Riemannian Manifolds with Flow Charts
AU - Edmond Cunningham
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28302
UR - https://arxiv.org/abs/2610.28302
AB - Riemannian manifolds are powerful models for problems with non-Euclidean structure. Recent work in geometric machine learning has focused on training deep neural networks to learn Riemannian metrics from high-dimensional data. However, many geometric algorithms require repeated evaluations of the exponential and logarithmic maps, whose high computational cost restricts the utility of learned Riemannian manifolds in practice. We propose to address this cost by training a conditional invertible neural network, called a flow chart, to approximate normal coordinates around points on a given Riemannian manifold. With this approach, the exponential and logarithmic maps can be approximated by fast Euclidean operations in the model's learned coordinate space. Our main contribution is an efficient loss function for training flow charts that is nonnegative and, under suitable domain assumptions, is zero precisely when the chart is normal. Across sixteen synthetic and data-derived geometries, flow charts are competitive with a specialized neural geodesic interpolator for logarithmic map estimation, while also being able to estimate the exponential map. When pretrained, flow charts provide a median speedup of 60-70x over numerical baselines at comparable logarithmic map estimation error, and their learned coordinates improve the accuracy of a numerical geodesic solver.
ER -