Local Constrained Bayesian Optimization
Not on the map. Why?
Abstract (arXiv)
Bayesian optimization (BO) for high-dimensional constrained problems remains a significant challenge due to the curse of dimensionality. We propose Local Constrained Bayesian Optimization (LCBO), a novel framework tailored for such settings. Unlike trust-region methods that are prone to premature shrinking when confronting tight or complex constraints, LCBO leverages the differentiable landscape of constraint-penalized surrogates to alternate between rapid local descent and uncertainty-driven exploration. Theoretically, we prove that LCBO achieves a convergence rate for the Karush-Kuhn-Tucker (KKT) residual that depends polynomially on the dimension d for common kernels under mild assumptions, offering a rigorous alternative to global BO where regret bounds typically scale exponentially. Extensive evaluations on high-dimensional benchmarks (up to 100D) demonstrate that LCBO consistently outperforms state-of-the-art baselines.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 52 references that are in the map. First posted on arXiv 9 Mar 2026.
Builds on
30 of 52 references.
References · 30
- 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 359
- 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
- 2021High-Dimensional Bayesian Optimization with Sparse Axis-Aligned Subspacescited by 139
- 2015High Dimensional Bayesian Optimisation and Bandits via Additive Modelscited by 137
- 2020Scalable Constrained Bayesian Optimizationcited by 84
- 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
- 2019Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspacescited by 73
- 2015Predictive Entropy Search for Bayesian Optimization with Unknown Constraintscited by 51
- 2022Constrained Efficient Global Optimization of Expensive Black-box Functionscited by 49
- 2021Local policy search with Bayesian optimizationcited by 37
- 2016Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangiancited by 29
- 2019An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraintscited by 29
18 more
- 2022Local Bayesian optimization via maximizing probability of descentcited by 29
- 2021TREGO: a Trust-Region Framework for Efficient Global Optimizationcited by 28
- 2021Sequential- and Parallel- Constrained Max-value Entropy Search via Information Lower Boundcited by 23
- 2022On Kernelized Multi-Armed Bandits with Constraintscited by 23
- 2020Rate-improved Inexact Augmented Lagrangian Method for Constrained Nonconvex Optimizationcited by 21
- 2019Constrained Bayesian Optimization with Max-Value Entropy Searchcited by 20
- 2022Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimizationcited by 19
- 2023The Behavior and Convergence of Local Bayesian Optimizationcited by 19
- 2023Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraintscited by 16
- 2024Variance-reduced first-order methods for deterministically constrained stochastic nonconvex optimization with strong convergence guaranteescited by 11
- 2021Bayesian Optimisation for Constrained Problemscited by 9
- 2022Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraintscited by 9
- 2024Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimizationcited by 9
- 2025NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Informationcited by 6
- 2026BayeSQP: Bayesian Optimization through Sequential Quadratic Programmingcited by 5
- 2024Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systemscited by 4
- 2023Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraintscited by 3
- 2025Convergence Rates of Constrained Expected Improvementcited by 2
Built on by
Not cited yet.