Functional Regression with Reconstructed Curves: Local Rank Stability and Optimized Confidence Certificates
- 1Laboratory of Statistics and Stochastic Processes, Djillali Liabès University, Sidi Bel Abbès 22000, Algeria
- 2Department of Mathematical Sciences, College of Science, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
Abstract
Reconstructing functional predictors can change nearest-neighbor ranks and introduce regression bias. Our contribution is a set of deterministic and probabilistic results quantifying these effects for an existing rank-weighted smoother. We distinguish direct pointwise inference, same-sample equivalence to the exact-curve estimator, and deterministic prediction-perturbation certification. A joint assignment relaxation bounds fitted-value changes. Under local radial-density and polynomial small-ball assumptions, local crowding gives a sufficient rank-stability rate and resolution condition; this is not a general infinite-dimensional rate. We adapt established threshold weighting to certified intervals with finite-sample coverage only when smoothness, conditional noise, and reconstruction-error upper bounds are valid independently of the response errors used in the interval. The numerical study comprises 20,175 simulated datasets, including irregular grids, Laplace measurement errors, and population principal-component truncation, with paired Monte Carlo uncertainty and neighborhood sensitivity analyses. Certified intervals remain substantially conservative, including after radius optimization. Predictive rankings vary with target location, and PCR outperforms the tested neighbor methods on Tecator. The Tecator experiment audits controlled coarsening of measured spectra; it does not validate inference for an unobserved continuous trajectory or provide prospective reconstruction calibration.
Related
- Stability Transfer for Autonomous Systems via Higher-Order Taylor-Truncated Lyapunov Certificates
- Iterative graph lifting for automatic design of path-complete stability certificates
- Data-to-Certificates (D2C): Koopman Supereigenfunctions for Stability, Safety, and Control
- When Gigawatts of Computational Load Disappear: Cycle-Space Certificates for Grid Synchronization and Transient Stability
- Optimizing Lyapunov Certificates via Stability-Preserving Quadratization for Polynomial Systems
BibTeX
@article{bouabsa2026functional,
title = {{Functional Regression with Reconstructed Curves: Local Rank Stability and Optimized Confidence Certificates}},
author = {Wahiba Bouabsa and Fatimah Alshahrani},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14213969},
url = {https://www.mdpi.com/2227-7390/14/21/3969},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Functional Regression with Reconstructed Curves: Local Rank Stability and Optimized Confidence Certificates
AU - Wahiba Bouabsa
AU - Fatimah Alshahrani
PY - 2026
DA - 2026/10/30
JO - Mathematics
DO - 10.3390/math14213969
UR - https://www.mdpi.com/2227-7390/14/21/3969
AB - Reconstructing functional predictors can change nearest-neighbor ranks and introduce regression bias. Our contribution is a set of deterministic and probabilistic results quantifying these effects for an existing rank-weighted smoother. We distinguish direct pointwise inference, same-sample equivalence to the exact-curve estimator, and deterministic prediction-perturbation certification. A joint assignment relaxation bounds fitted-value changes. Under local radial-density and polynomial small-ball assumptions, local crowding gives a sufficient rank-stability rate and resolution condition; this is not a general infinite-dimensional rate. We adapt established threshold weighting to certified intervals with finite-sample coverage only when smoothness, conditional noise, and reconstruction-error upper bounds are valid independently of the response errors used in the interval. The numerical study comprises 20,175 simulated datasets, including irregular grids, Laplace measurement errors, and population principal-component truncation, with paired Monte Carlo uncertainty and neighborhood sensitivity analyses. Certified intervals remain substantially conservative, including after radius optimization. Predictive rankings vary with target location, and PCR outperforms the tested neighbor methods on Tecator. The Tecator experiment audits controlled coarsening of measured spectra; it does not validate inference for an unobserved continuous trajectory or provide prospective reconstruction calibration.
SN - 2227-7390
ER -