Sequential sparse Gaussian process quantile regression
Abstract
Quantile regression aims to estimate the conditional quantiles of a response variable from observed data. In a Bayesian setting, Gaussian process quantile regression provides uncertainty quantification but faces significant computational challenges due to the nonconjugacy of the asymmetric Laplace likelihood and the cost of posterior inference. We develop a sparse Gaussian process framework in which the quantile function is represented through a reduced set of inducing variables and posterior inference is performed using a Laplace approximation. A decomposition of the predictive uncertainty into conditional-prior and posterior-induced variance components is then exploited to drive two complementary adaptive mechanisms: inducing-input infilling and data acquisition. These mechanisms are combined within a sequential algorithm that allocates computational effort toward the dominant source of predictive uncertainty and adaptively controls model complexity. Numerical experiments on benchmark problems demonstrate the accuracy of the Laplace approximation, the benefits of variance-based inducing-input placement, and the effectiveness of the proposed sequential enrichment strategy compared with predefined data-acquisition strategies. The method is finally applied to ship seakeeping under forecast uncertainty, where it outperforms a replication-based counterpart from the literature under limited simulation budgets.
Related
- On Basis Function Selection for Sparse Gaussian Process Regression
- Sparse-group Convoluted Smoothed Quantile Regression in High Dimension
- Decentralized Sparse Quantile Regression
- Multiscale Sequential Auditing of Quantile Regression with Point Masses
- A Gaussian Process Regression-Enhanced Two-Sweep Parameterized Power Method for Computing Extreme Eigenpairs
BibTeX
@misc{nicolas2026sequential,
title = {{Sequential sparse Gaussian process quantile regression}},
author = {Hugo Nicolas and Olivier Le Maître},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.31284},
eprint = {2606.31284},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05672861v2},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Sequential sparse Gaussian process quantile regression
AU - Hugo Nicolas
AU - Olivier Le Maître
PY - 2026
DA - 2026/10/21
PB - HAL
DO - 10.48550/arxiv.2606.31284
UR - https://hal.science/hal-05672861v2
AB - Quantile regression aims to estimate the conditional quantiles of a response variable from observed data. In a Bayesian setting, Gaussian process quantile regression provides uncertainty quantification but faces significant computational challenges due to the nonconjugacy of the asymmetric Laplace likelihood and the cost of posterior inference. We develop a sparse Gaussian process framework in which the quantile function is represented through a reduced set of inducing variables and posterior inference is performed using a Laplace approximation. A decomposition of the predictive uncertainty into conditional-prior and posterior-induced variance components is then exploited to drive two complementary adaptive mechanisms: inducing-input infilling and data acquisition. These mechanisms are combined within a sequential algorithm that allocates computational effort toward the dominant source of predictive uncertainty and adaptively controls model complexity. Numerical experiments on benchmark problems demonstrate the accuracy of the Laplace approximation, the benefits of variance-based inducing-input placement, and the effectiveness of the proposed sequential enrichment strategy compared with predefined data-acquisition strategies. The method is finally applied to ship seakeeping under forecast uncertainty, where it outperforms a replication-based counterpart from the literature under limited simulation budgets.
ER -