高效并行大规模排序与选择的'聚类与征服'流程
Sample-Efficient "Clustering and Conquer" Procedures for Parallel Large-Scale Ranking and Selection
AI总结：
本文提出一种高效的并行大规模排序与选择方法，通过引入聚类步骤提升样本效率，适用于大规模AI应用。
摘要：
本文旨在通过利用相关性信息提高并行大规模排序与选择（R&S）问题的样本效率。我们通过在并行计算中常用的'分而治之'框架中添加基于相关性的聚类步骤，将其转变为'聚类与征服'。在对称基准场景下的分析结果表明，这种看似简单的修改为广泛使用的样本最优R&S流程带来了O(p)的样本复杂度减少。我们的方法有两个关键优势：1）它不需要高度准确的相关性估计或精确的聚类；2）它允许无缝集成各种现有的R&S流程，同时实现最优的样本复杂度。理论上，我们开发了一种新的梯度分析框架来分析样本效率并指导大规模R&S流程的设计。我们还引入了一种专为大规模场景设计的新型并行聚类算法。最后，在大规模AI应用如神经网络架构搜索中，我们的方法展示了优越的性能。
英文摘要：
This work aims to improve the sample efficiency of parallel large-scale ranking and selection (R&S) problems by leveraging correlation information. We modify the commonly used "divide and conquer" framework in parallel computing by adding a correlation-based clustering step, transforming it into "clustering and conquer". Theoretically, we develop a novel gradient-based analysis framework and show that this seemingly simple modification substantially improves the performance of large-scale R&S procedures. Our approach enjoys two key advantages: (1) it does not require highly accurate correlation estimation or precise clustering, and (2) it can be seamlessly integrated with various existing fixed-precision and fixed-budget R&S procedures while achieving optimal sample complexity. We also introduce a new parallel clustering algorithm tailored to large-scale settings. Finally, in large-scale AI applications such as neural architecture search, our methods demonstrate superior performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
