期刊
IEEE TRANSACTIONS ON SIGNAL PROCESSING
卷 60, 期 8, 页码 4289-4305出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSP.2012.2198470
关键词
Biological networks; convergence; diffusion adaptation; distributed optimization; energy conservation; incremental techniques; learning; mean-square performance; stability
资金
- NSF [CCF-1011918, CCF-0942936]
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [1011918] Funding Source: National Science Foundation
We propose an adaptive diffusion mechanism to optimize global cost functions in a distributed manner over a network of nodes. The cost function is assumed to consist of a collection of individual components. Diffusion adaptation allows the nodes to cooperate and diffuse information in real-time; it also helps alleviate the effects of stochastic gradient noise and measurement noise through a continuous learning process. We analyze the mean-square-error performance of the algorithm in some detail, including its transient and steady-state behavior. We also apply the diffusion algorithm to two problems: distributed estimation with sparse parameters and distributed localization. Compared to well-studied incremental methods, diffusion methods do not require the use of a cyclic path over the nodes and are robust to node and link failure. Diffusion methods also endow networks with adaptation abilities that enable the individual nodes to continue learning even when the cost function changes with time. Examples involving such dynamic cost functions with moving targets are common in the context of biological networks.
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