期刊
AUTOMATICA
卷 159, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.automatica.2023.111363
关键词
Decentralized stochastic optimization; Saddle-point algorithm; Compression; Sample feedback; Bandit feedback
This paper investigates a multi-agent network where each node has a stochastic cost function that depends on its decision variable and a random variable. The network aims to minimize an aggregate objective function composed of the expected values of the local cost functions, subject to pairwise constraints. The paper develops decentralized saddle-point algorithms and obtains performance bounds for two different models of local information availability at the nodes. The results show that compressed communication between neighbors does not affect the performance significantly.
We consider a multi-agent network where each node has a stochastic (local) cost function that depends on the decision variable of that node and a random variable, and further, the decision variables of neighboring nodes are pairwise constrained. There is an aggregated objective function for the network, composed additively of the expected values of the local cost functions at the nodes, and the overall goal of the network is to obtain the minimizing solution to this aggregate objective function subject to all the pairwise constraints. This is to be achieved at the level of the nodes using decentralized information and local computation, with exchanges of only compressed information allowed by neighboring nodes. The paper develops algorithms and obtains performance bounds for two different models of local information availability at the nodes: (i) sample feedback, where each node has direct access to samples of the local random variable to evaluate its local cost, and (ii) bandit feedback, where samples of the random variables are not available, but only the values of the local cost functions at two random points close to the decision are available to each node. For both models, with compressed communication between neighbors, we have developed decentralized saddle-point algorithms that deliver performances no different (in order sense) from those without communication compression; specifically, we show that deviation from the global minimum value and violations of the constraints are upper-bounded by O(T- 2 ) and O(T- 1 1 4 ), respectively, where T is the number of iterations. Numerical examples provided in the paper corroborate these bounds.(c) 2023 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据