Consensus and Diffusion for First-Order Distributed Optimization Over Multi-Hop Network

Consensus and Diffusion for First-Order Distributed Optimization Over Multi-Hop Network

Distributed optimization is a powerful paradigm to solve various problems in machine learning over networked systems. Existing first-order optimization methods perform cheap gradient descent by exchanging information per iteration only with single-hop neighbours in a network. However, in many agent...

Full description

Bibliographic Details
Main Authors: Mou Wu, Haibin Liao, Liansheng Tan, Guonian Jin, Liangji Zhong, Yonggang Xiao, Zhiyong Wang
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Distributed optimization
gradient descent
consensus
diffusion
multi-hop network
Online Access:https://ieeexplore.ieee.org/document/10188685/

Internet

https://ieeexplore.ieee.org/document/10188685/

Similar Items