STREGO: A Scalable Implementation of a Trust-Region Framework for Noisy Bayesian Optimization
Abstract
TREGO, a trust-region Bayesian optimization (BO) method for expensive blackbox problems, has convergence guarantees, but only for exact function values. In high dimension, its performance tends to deteriorate. This paper asks whether a trust-region BO method can be extended to handle noisy evaluations while being competitive in high dimension. We first generalize TREGO into a trust-region framework for noisy BO and extend its convergence analysis to noisy function estimates that are sufficiently accurate with sufficiently high probability. We then propose STREGO, a scalable implementation of this framework. Its global phase selects a batch of candidates by solving a bi-objective problem on the posterior mean of a Gaussian process and the integrated variance reduction. Unlike the predictive variance, this second objective does not favor boundary points merely because they are far from the data. Its local phase minimizes the posterior mean of a second Gaussian process, trained only on points close to the incumbent. STREGO is compared with TREGO, TURBO, BAXUS and NSMA-BO on synthetic and real-world problems of dimension $4$ to $124$, with and without noise. It gives the best average results in every synthetic setting tested and the best or tied-best solution on four of the six real-world problems. An implementation of STREGO is available at https://github.com/Mayousk/STREGO.
Related
- MF-SCBO : Multi-fidelity Scalable Constrained Bayesian Optimization
- ISBO: Scalable Spatio-Temporal Bayesian Optimization with Log Gaussian Cox Process Models via the INLA-SPDE Approach
- Recursive moment updates for scalable Bayesian nonparametric regression
- Scalable Bayesian Inference for Time Series via Divide and Conquer
- Compressed Active Subspaces for Scalable Bayesian Inference
BibTeX
@misc{diouane2026strego,
title = {{STREGO: A Scalable Implementation of a Trust-Region Framework for Noisy Bayesian Optimization}},
author = {Youssef Diouane and Issmail El Hallaoui and Meisseme Kadri and Amina Lamghari},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.14338},
eprint = {2610.14338},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.14338},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - STREGO: A Scalable Implementation of a Trust-Region Framework for Noisy Bayesian Optimization
AU - Youssef Diouane
AU - Issmail El Hallaoui
AU - Meisseme Kadri
AU - Amina Lamghari
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.14338
UR - https://arxiv.org/abs/2610.14338
AB - TREGO, a trust-region Bayesian optimization (BO) method for expensive blackbox problems, has convergence guarantees, but only for exact function values. In high dimension, its performance tends to deteriorate. This paper asks whether a trust-region BO method can be extended to handle noisy evaluations while being competitive in high dimension. We first generalize TREGO into a trust-region framework for noisy BO and extend its convergence analysis to noisy function estimates that are sufficiently accurate with sufficiently high probability. We then propose STREGO, a scalable implementation of this framework. Its global phase selects a batch of candidates by solving a bi-objective problem on the posterior mean of a Gaussian process and the integrated variance reduction. Unlike the predictive variance, this second objective does not favor boundary points merely because they are far from the data. Its local phase minimizes the posterior mean of a second Gaussian process, trained only on points close to the incumbent. STREGO is compared with TREGO, TURBO, BAXUS and NSMA-BO on synthetic and real-world problems of dimension $4$ to $124$, with and without noise. It gives the best average results in every synthetic setting tested and the best or tied-best solution on four of the six real-world problems. An implementation of STREGO is available at https://github.com/Mayousk/STREGO.
ER -