![](/images/graphics-bg.png)
A Distributed Conjugate Gradient Online Learning Method over Networks
Joint Authors
Wu, Qingtao
Zhu, Junlong
Xu, Cuixia
Shang, Youlin
Source
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-03-11
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
In a distributed online optimization problem with a convex constrained set over an undirected multiagent network, the local objective functions are convex and vary over time.
Most of the existing methods used to solve this problem are based on the fastest gradient descent method.
However, the convergence speed of these methods is decreased with an increase in the number of iterations.
To accelerate the convergence speed of the algorithm, we present a distributed online conjugate gradient algorithm, different from a gradient method, in which the search directions are a set of vectors that are conjugated to each other and the step sizes are obtained through an accurate line search.
We analyzed the convergence of the algorithm theoretically and obtained a regret bound of OT, where T is the number of iterations.
Finally, numerical experiments conducted on a sensor network demonstrate the performance of the proposed algorithm.
American Psychological Association (APA)
Xu, Cuixia& Zhu, Junlong& Shang, Youlin& Wu, Qingtao. 2020. A Distributed Conjugate Gradient Online Learning Method over Networks. Complexity،Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1139898
Modern Language Association (MLA)
Xu, Cuixia…[et al.]. A Distributed Conjugate Gradient Online Learning Method over Networks. Complexity No. 2020 (2020), pp.1-13.
https://search.emarefa.net/detail/BIM-1139898
American Medical Association (AMA)
Xu, Cuixia& Zhu, Junlong& Shang, Youlin& Wu, Qingtao. A Distributed Conjugate Gradient Online Learning Method over Networks. Complexity. 2020. Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1139898
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1139898