计算机科学
强化学习
随机逼近
比例(比率)
系列(地层学)
纪元(天文学)
当地时间
数学优化
随机过程
分布式计算
人工智能
数学
计算机安全
量子力学
生物
统计
物理
计算机视觉
星星
古生物学
钥匙(锁)
标识
DOI:10.1109/icc54714.2021.9703179
摘要
In this paper, we consider a distributed variant of the popular two-time-scale stochastic approximation, where there are a group of agents communicating with a centralized coordinator. The goal of the agents is to find the roots of two coupling operators composed of the local operators at the agents. Such a framework models many practical problems in different areas, including those in federated learning and reinforcement learning. Over a series of time epoch, each agent runs a number of local two-time-scale stochastic approximation steps based on its own data, whose results are then aggregated at the centralized coordinator. Our main contribution is to characterize the finite-time performance of the local two-time-scale stochastic approximation, where we provide explicit formulas for the rate of this method.
科研通智能强力驱动
Strongly Powered by AbleSci AI