Adaptive Replication Strategies in Trust-Region-Based Bayesian Optimization of Stochastic Functions
Not on the map. Why?
Abstract (arXiv)
We develop and analyze a method for stochastic simulation optimization based on Gaussian process models within a trust-region framework. We focus on settings where the variance of the objective function is large, making accurate estimation challenging and often requiring many evaluations. To address this regime, we combine local modeling with adaptive replication, allowing the method to allocate repeated evaluations where they are most beneficial. We introduce several mechanisms to promote and adapt replication, including modifications to the acquisition function and cost-aware evaluation strategies. These components enable our approach to scale effectively when high levels of sampling are required to reduce noise. We refer to the resulting method as OGPIT, for Optimization by Gaussian Processes In Trust regions. Numerical experiments show that adaptive replication can substantially improve computational efficiency while preserving solution accuracy compared to baseline methods, in particular when evaluation costs are taken into account.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 71 references that are in the map. First posted on arXiv 29 Apr 2025.
Builds on
28 of 71 references.
References · 28
- 2020Variational Quantum Algorithmscited by 692
- 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 374
- 2016Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasetscited by 132
- 2017Multi-fidelity Bayesian Optimisation with Continuous Approximationscited by 121
- 2019Exact Gaussian Processes on a Million Data Pointscited by 119
- 2017Constrained Bayesian Optimization with Noisy Experimentscited by 104
- 2020HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisationcited by 83
- 2021A survey on high-dimensional Gaussian process modeling with application to Bayesian optimizationcited by 77
- 2013Local Gaussian process approximation for large computer experimentscited by 59
- 2015MCMC for Variationally Sparse Gaussian Processescited by 44
- 2016Practical heteroskedastic Gaussian process modeling for large simulation experimentscited by 39
- 2015GLASSES: Relieving The Myopia Of Bayesian Optimisationcited by 38
16 more
- 2023Inducing Point Allocation for Sparse Gaussian Processes in High-Throughput Bayesian Optimisationcited by 32
- 2017Replication or exploration? Sequential design for stochastic simulation experimentscited by 30
- 2022Local Bayesian optimization via maximizing probability of descentcited by 30
- 2021TREGO: a Trust-Region Framework for Efficient Global Optimizationcited by 29
- 2018Optimization, fast and slow: optimally switching between local and Bayesian optimizationcited by 22
- 2023The Behavior and Convergence of Local Bayesian Optimizationcited by 20
- 2023Comparison of High-Dimensional Bayesian Optimization Algorithms on BBOBcited by 19
- 2015Differentiating the multipoint Expected Improvement for optimal batch designcited by 13
- 2018Evaluating Gaussian Process Metamodels and Sequential Designs for Noisy Level Set Estimationcited by 10
- 2021A portfolio approach to massively parallel Bayesian optimizationcited by 9
- 2022Scalable Gaussian-process regression and variable selection using Vecchia approximationscited by 8
- 2016ASTRO-DF: A Class of Adaptive Sampling Trust-Region Algorithms for Derivative-Free Stochastic Optimizationcited by 7
- 2022Movement Penalized Bayesian Optimization with Application to Wind Energy Systemscited by 7
- 2017A trust-region method for derivative-free nonlinear constrained stochastic optimizationcited by 3
- 2022Accelerating Noisy VQE Optimization with Gaussian Processescited by 1
- 2024A Novel Noise-Aware Classical Optimizer for Variational Quantum Algorithmscited by 1
Built on by
Not cited yet.