arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.06310math.OC
收藏

分布式约束在线学习

Distributed Constrained Online Learning

Santiago Paternain, Soomin Lee, Michael M. Zavlanos, Alejandro Ribeiro

摘要:

在本文中,我们考虑在网络中的代理选择行动,以满足一组随时间任意变化的约束,并尽量减少时变函数,他们只有本地的意见。行动的选择,也称为战略,是因果关系和分散的,即,确定给定代理的动作的动力系统仅取决于当前时间的约束以及它自己的动作和它的邻居的动作。为了确定这样一个战略,我们提出了一个分散的鞍点算法,并表明相应的全球配合和遗憾有界的功能的顺序$\sqrt{T}$。具体来说,我们定义的战略作为一个向量,随着时间的推移,集成的全局约束违反所看到的一个给定的节点的全局适合。拟合是与在线操作相关联的性能损失,而不是离线透视操作,离线透视操作总是可以选择一个动作,如果存在的话,它总是满足约束。如果这种拟合随时间范围呈次线性增长,则表明该策略接近可行的行动集。同样地,我们将策略的后悔定义为它的累积成本与预先知道目标函数的时间演化的最佳固定行动的累积成本之间的差。数值例子支持理论结论。

英文摘要:

In this paper, we consider groups of agents in a network that select actions in order to satisfy a set of constraints that vary arbitrarily over time and minimize a time-varying function of which they have only local observations. The selection of actions, also called a strategy, is causal and decentralized, i.e., the dynamical system that determines the actions of a given agent depends only on the constraints at the current time and on its own actions and those of its neighbors. To determine such a strategy, we propose a decentralized saddle point algorithm and show that the corresponding global fit and regret are bounded by functions of the order of $\sqrt{T}$. Specifically, we define the global fit of a strategy as a vector that integrates over time the global constraint violations as seen by a given node. The fit is a performance loss associated with online operation as opposed to offline clairvoyant operation which can always select an action if one exists, that satisfies the constraints at all times. If this fit grows sublinearly with the time horizon it suggests that the strategy approaches the feasible set of actions. Likewise, we define the regret of a strategy as the difference between its accumulated cost and that of the best fixed action that one could select knowing beforehand the time evolution of the objective function. Numerical examples support the theoretical conclusions.

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。

↑