Positive, monotone, and convex Gaussian process regression with Laplacian eigenfunctions
Abstract
We study how to condition an existing Hilbert space Gaussian process (HSGP) expansion on positivity, monotonicity, or convexity throughout an interval. The expansion has Gaussian coefficients whose variances are given by the kernel's spectral density. At fixed covariance and noise parameters, we retain this coefficient law and represent each complete interval event as a threshold on one coefficient. Integrating out that coefficient gives a strongly log-concave marginal posterior with a normal survival weight, while conditional truncated normal sampling recovers the full constrained law. The construction also covers joint restrictions within the finite expansion. For individual restrictions, we characterize the thresholds through polynomial equations and bound posterior error from conservative numerical evaluation in total variation. Under spectral regularity, the conditioned finite posteriors converge in quadratic Wasserstein distance to the corresponding conditioned underlying GP posteriors as the computational interval expands and higher frequencies are retained. This convergence controls uniform discrepancies in the response and derivatives through the constrained order. Mercury lidar and leaf light-response applications illustrate the consequences for derivative inference.
Related
- Absolute Continuity of Monotone Aggregations under Positive Regression Dependence
- Corner Regularity of Laplacian Eigenfunctions
- Eigenvalues and eigenfunctions of the fractional Laplacian on the interval
- Principal Component Regression Dominates all Monotone Spectral Filters for Linear Regression
- An Explicit Family of Log-Concave Counterexamples to the Gaussian Completely Monotone Conjecture
BibTeX
@misc{jensen2026positive,
title = {{Positive, monotone, and convex Gaussian process regression with Laplacian eigenfunctions}},
author = {Andreas Kryger Jensen},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27177},
eprint = {2610.27177},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27177},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Positive, monotone, and convex Gaussian process regression with Laplacian eigenfunctions
AU - Andreas Kryger Jensen
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.27177
UR - https://arxiv.org/abs/2610.27177
AB - We study how to condition an existing Hilbert space Gaussian process (HSGP) expansion on positivity, monotonicity, or convexity throughout an interval. The expansion has Gaussian coefficients whose variances are given by the kernel's spectral density. At fixed covariance and noise parameters, we retain this coefficient law and represent each complete interval event as a threshold on one coefficient. Integrating out that coefficient gives a strongly log-concave marginal posterior with a normal survival weight, while conditional truncated normal sampling recovers the full constrained law. The construction also covers joint restrictions within the finite expansion. For individual restrictions, we characterize the thresholds through polynomial equations and bound posterior error from conservative numerical evaluation in total variation. Under spectral regularity, the conditioned finite posteriors converge in quadratic Wasserstein distance to the corresponding conditioned underlying GP posteriors as the computational interval expands and higher frequencies are retained. This convergence controls uniform discrepancies in the response and derivatives through the constrained order. Mercury lidar and leaf light-response applications illustrate the consequences for derivative inference.
ER -