Multi-Agent Bayesian Optimization with Coupled Black-Box and Affine Constraints
Not on the map. Why?
Abstract (arXiv)
This paper studies the problem of distributed multi-agent Bayesian optimization with both coupled black-box constraints and known affine constraints. A primal-dual distributed algorithm is proposed that achieves similar regret/violation bounds as those in the single-agent case for the black-box objective and constraint functions. Additionally, the algorithm guarantees an O(N√T) bound on the cumulative violation for the known affine constraints, where N is the number of agents. Hence, it is ensured that the average of the samples satisfies the affine constraints up to the error O(N/√T). Furthermore, we characterize certain conditions under which our algorithm can bound a stronger metric of cumulative violation and provide best-iterate convergence without affine constraint. The method is then applied to both sampled instances from Gaussian processes and a real-world optimal power allocation problem for wireless communication; the results show that our method simultaneously provides close-to-optimal performance and maintains minor violations on average, corroborating our theoretical analysis.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 46 references that are in the map. First posted on arXiv 2 Oct 2023.
Builds on
22 of 46 references.
References · 22
- 2018A Tutorial on Bayesian Optimizationcited by 734
- 2017On Kernelized Multi-armed Banditscited by 348
- 2020On Information Gain and Regret Bounds in Gaussian Process Banditscited by 156
- 2015High Dimensional Bayesian Optimisation and Bandits via Additive Modelscited by 137
- 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
- 2014Bayesian Optimization with Unknown Constraintscited by 109
- 2017Online Convex Optimization with Stochastic Constraintscited by 94
- 2016The Parallel Knowledge Gradient Method for Batch Bayesian Optimizationcited by 73
- 2018What Doubling Tricks Can and Can't Do for Multi-Armed Banditscited by 69
- 2018High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groupscited by 58
- 2022Constrained Efficient Global Optimization of Expensive Black-box Functionscited by 49
- 2022Provably Efficient Model-Free Constrained RL with Linear Function Approximationcited by 29
10 more
- 2022On Kernelized Multi-Armed Bandits with Constraintscited by 23
- 2021VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraintscited by 10
- 2022Rectified Pessimistic-Optimistic Learning for Stochastic Continuum-armed Bandit with Constraintscited by 9
- 2023Gaussian Max-Value Entropy Search for Multi-Agent Bayesian Optimizationcited by 7
- 2023Violation-Aware Contextual Bayesian Optimization for Controller Performance Optimization with Unmodeled Constraintscited by 5
- 2020Hierarchical Multi-Agent Optimization for Resource Allocation in Cloud Computingcited by 4
- 2019A Probabilistic Approach for Demand-Aware Ride-Sharing Optimizationcited by 2
- 2019Dissipativity in economic model predictive control: beyond steady-state optimalitycited by 2
- 2022Optimizing Two-Truck Platooning with Deadlinescited by 2
- 2023Multi-agent Black-box Optimization using a Bayesian Approach to Alternating Direction Method of Multiplierscited by 1
Built on by
Not cited yet.