arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.07836eess.SYcs.SY
收藏

连续时间分布式随机梯度算法的收敛性分析

Convergence Analysis of Continuous-Time Distributed Stochastic Gradient Algorithms

College of Electrical Engineering and Automation, Shandong University of Science and Technology(山东科技大学电气工程学院);School of Electrical Engineering and Automation, Jiangsu Normal University(江苏师范大学电气工程学院)

Jianhua Sun, Kaihong Lu, Xin Yu

AI总结:

本文提出连续时间分布式随机梯度算法,用于解决分布式优化问题,通过布朗运动描述随机性,并证明算法在期望意义上收敛到共同最小值。

摘要:

本文提出了一种新的框架,用于研究通过多智能体系统连续时间动态来研究分布式优化问题中的随机梯度。这里的智能体目标是合作最小化凸目标函数的总和。在做决策时,每个智能体只能访问其自身目标函数的随机梯度,而不是真实的梯度,并且可以通过时间变化的定向图与邻居交换局部状态信息。特别是,随机性通过布朗运动来描述。为了解决这个问题,我们提出了一种基于共识算法和梯度下降策略的连续时间分布式随机梯度算法。在对图的连通性和目标函数的轻微假设下,利用凸分析理论、李雅普诺夫理论和伊藤公式,我们证明了智能体的状态在期望意义上渐近达到共同的最小值。最后,通过一个模拟示例来展示我们理论结果的有效性。

英文摘要:

In this paper, we propose a new framework to study distributed optimization problems with stochastic gradients by employing a multi-agent system with continuous-time dynamics. Here the goal of the agents is to cooperatively minimize the sum of convex objective functions. When making decisions, each agent only has access to a stochastic gradient of its own objective function rather than the real gradient, and can exchange local state information with its immediate neighbors via a time-varying directed graph. Particularly, the stochasticity is depicted by the Brownian motion. To handle this problem, we propose a continuous-time distributed stochastic gradient algorithm based on the consensus algorithm and the gradient descent strategy. Under mild assumptions on the connectivity of the graph and objective functions, using convex analysis theory, the Lyapunov theory and Ito formula, we prove that the states of the agents asymptotically reach a common minimizer in expectation. Finally, a simulation example is worked out to demonstrate the effectiveness of our theoretical results.

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。

↑