有限预算下的最佳臂识别
机器学习
2026-03-02 v1
摘要
在许多应用场景中，对不同方案有效性的评估会消耗不同的成本或资源。针对这种资源消耗的异质性问题，我们研究了最佳臂识别带资源约束问题（BAIwRC），其中智能体需在资源约束条件下识别最佳方案（即臂）。每调用一次臂都消耗一种或多种有限资源。我们的工作作出两个关键贡献：首先，我们提出了带资源配额的 successive halving 算法（SH-RR），将资源感知的分配集成到经典的 successive halving 框架中用于最佳臂识别。SH-RR 算法统一了随机消耗场景和确定性消耗场景下的理论分析，并引入了一种新的有效消耗度量。
引用
@article{arxiv.2602.24146,
title = {Learning with a Budget: Identifying the Best Arm with Resource Constraints},
author = {Zitian Li and Wang Chi Cheung},
journal= {arXiv preprint arXiv:2602.24146},
year = {2026}
}
备注
A preliminary version of this work, titled 'Best Arm Identification with Resource Constraints,' was presented at the 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024). This manuscript extends the original conference paper by providing improved theoretical results and more generalized conclusions, aiming for future journal submission. arXiv admin note: substantial text overlap with arXiv:2402.19090