Sampling Design and Confidence Tubes for Integral Curves on Riemannian Manifolds
Organizations: Division of Mathematical Sciences, Nanyang Technological University · School of Statistics and Data Science, Shanghai University of Finance and Economics · Department of Mathematics, Ruhr University Bochum
Abstract
We estimate the integral curve of an unknown vector field from noisy tangent vector field on a known compact Riemannian manifold. We consider two sampling settings: independent observations at random locations that have already been collected, and a fixed response budget that allows subsequent locations to be chosen using pilot information. Under suitable regularity assumptions, the passive kernel estimator has curve error of order in probability, with sample size and manifold dimension . Its functional central limit theorem has a limit characterized by a linear stochastic differential equation. For active sampling, an independent pilot directs one new batch of measurements to neighborhoods of the target curve. Under localization, smoothness and design conditions, this concentration yields expected maximum curve error of order , including the pilot in the total response budget . Both methods provide simultaneous geodesic confidence tubes with asymptotically exact coverage under mild conditions. Simulations show narrower active tubes in most reported settings, with improved small-sample coverage in some three-dimensional examples. Ocean-drifter observations illustrate mean-flow reconstruction on the sphere, and a canopy-flow LDA application uses retrospective active sampling to quantify lateral and vertical departures of local mean streamlines.
Figures & tables
| Coverage (%) | Bias | Radius | Coverage (%) | Bias | Radius | Coverage (%) | Bias | Radius | |
|---|---|---|---|---|---|---|---|---|---|
| 200 | 95.2 | 0.046 | 0.390 | 89.6 | 0.066 | 0.158 | 87.8 | 0.084 | 0.188 |
| 400 | 96.0 | 0.027 | 0.212 | 92.6 | 0.046 | 0.140 | 93.0 | 0.055 | 0.166 |
| 600 | 96.6 | 0.021 | 0.166 | 93.8 | 0.036 | 0.131 | 93.0 | 0.043 | 0.157 |
| 800 | 96.6 | 0.018 | 0.133 | 96.8 | 0.026 | 0.125 | 94.4 | 0.035 | 0.149 |
| 1000 | 95.6 | 0.016 | 0.122 | 96.4 | 0.024 | 0.121 | 93.6 | 0.033 | 0.145 |
| Coverage (%) | Bias | Radius | Coverage (%) | Bias | Radius | Coverage (%) | Bias | Radius | |
|---|---|---|---|---|---|---|---|---|---|
| 200 | 94.0 | 17.762 | 0.139 | 97.2 | 14.666 | 0.237 | 97.6 | 10.827 | 0.172 |
| 400 | 95.2 | 5.171 | 0.083 | 97.6 | 3.175 | 0.097 | 95.8 | 3.664 | 0.088 |
| 600 | 95.2 | 4.487 | 0.060 | 96.8 | 7.527 | 0.115 | 97.8 | 2.227 | 0.098 |
| 800 | 94.0 | 4.742 | 0.050 | 97.0 | 2.853 | 0.080 | 96.2 | 3.116 | 0.070 |
| 1000 | 94.2 | 3.600 | 0.045 | 97.2 | 1.990 | 0.064 | 96.0 | 1.830 | 0.058 |
Confidence Region Estimation
Confidence region estimation builds sets around unknown parameters or predictions that quantify uncertainty while controlling coverage.
See all 44 papers