2024/02/03 by Zishi Zhang, Yijie Peng, Zhang, Zishi +1
Computer Science · Decision Sciences · #Data Management and Algorithms #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Methodology (stat.ME) #Multi-Criteria Decision Making
paper · pdf · doi:10.48550/arxiv.2402.02196
openalex publication_date 2024/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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". Analytical results under a symmetric benchmark scenario show that this seemingly simple modification yields an O(p) reduction in sample complexity for a widely used class of sample-optimal R&S procedures. Our approach enjoys two key advantages: 1) it does not require highly accurate correlation estimation or precise clustering, and 2) it allows for seamless integration with various existing R&S procedures, while achieving optimal sample complexity. Theoretically, we develop a novel gradient analysis framework to analyze sample efficiency and guide the design of large-scale R&S procedures. We also introduce a new parallel clustering algorithm tailored for large-scale scenarios. Finally, in large-scale AI applications such as neural architecture search, our methods demonstrate superior performance.