arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.05445math.OCcs.MA
收藏

开放多智能体系统中分散梯度下降的稳定性

Stability of Decentralized Gradient Descent in Open Multi-Agent Systems

Julien M. Hendrickx, Michael G. Rabbat

摘要:

分散梯度下降(DGD)的目的是最小化互联代理持有的$n$函数的总和。我们研究了DGD的稳定性,在开放的背景下,代理可以加入或离开系统,导致每次在添加或删除其功能的全球目标。假设所有的功能是光滑的,强凸的,和他们的极小都躺在一个给定的球,我们的特点是这些功能的总和的全局极小的灵敏度,以去除或添加一个新的功能,并提供界在$ O\left(\min \left(κ^{0.5}, κ/n^{0.5},κ^{1.5}/n\right)\right)$其中$κ$是条件数。我们还表明,所有代理的状态最终可以有界的到达和离开的序列无关。边界的大小与互连的重要性成比例,这也决定了在没有到达和离开的情况下最终解的准确性,从而暴露了准确性和灵敏度之间的潜在权衡。我们的分析依赖于制定DGD作为梯度下降的辅助功能。我们的结果的紧密性进行了分析,使用PESTO?

英文摘要:

The aim of decentralized gradient descent (DGD) is to minimize a sum of $n$ functions held by interconnected agents. We study the stability of DGD in open contexts where agents can join or leave the system, resulting each time in the addition or the removal of their function from the global objective. Assuming all functions are smooth, strongly convex, and their minimizers all lie in a given ball, we characterize the sensitivity of the global minimizer of the sum of these functions to the removal or addition of a new function and provide bounds in $ O\left(\min \left(κ^{0.5}, κ/n^{0.5},κ^{1.5}/n\right)\right)$ where $κ$ is the condition number. We also show that the states of all agents can be eventually bounded independently of the sequence of arrivals and departures. The magnitude of the bound scales with the importance of the interconnection, which also determines the accuracy of the final solution in the absence of arrival and departure, exposing thus a potential trade-off between accuracy and sensitivity. Our analysis relies on the formulation of DGD as gradient descent on an auxiliary function. The tightness of our results is analyzed using the PESTO Toolbox.

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。

↑