Convergence and Inference of Stream Stochastic Gradient Descent, with Applications to Queueing Systems and Inventory Control

• 成果类型: Article
• 署名作者: Li, Xiang; Liang, Jiadong; Chen, Xinyun; Zhang, Zhihua
• 署名单位: Peking University; The Chinese University of Hong Kong, Shenzhen
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.2025.1662
• 发表日期: 2026
• 关键词: STATISTICAL-INFERENCE; gi/g/1 queue; approximation; optimization; simulation; algorithm

摘要

Stream stochastic gradient descent (SGD) is a simple and efficient method for solving online optimization problems in operations research (OR), where data are generated by parameter-dependent Markov chains. Unlike traditional approaches which require increasing batch sizes during iterations, stream SGD uses a single sample per iteration, significantly improving sample efficiency. This paper establishes a systematic framework for analyzing stream SGD, leveraging the Poisson equation solution to address gradient bias and statistical dependence. We prove optimal O(T-1) convergence rates and the state-ofthe-art O(logT) regret, while also introducing an online inference method for uncertainty quantification and supporting it by a novel functional central limit theorem. We propose a novel Wasserstein-type divergence to describe the framework's conditions, which makes the assumptions in question directly verified via coupling techniques tailored to underlying OR models. We consider applications in queueing systems and inventory management, demonstrating the practicality and broad relevance, as well as providing new insights into the effectiveness of stream SGD in OR fields.