Hybrid Distributed Optimization for Learning Over Networks With Heterogeneous Agents

Hybrid Distributed Optimization for Learning Over Networks With Heterogeneous Agents

This paper considers distributed optimization for learning problems over networks with heterogeneous agents having different computational capabilities. The heterogeneity of computational capabilities implies that a subset of the agents may run computationally-intensive learning algorithms like Newt...

Full description

Bibliographic Details
Main Authors: Mohammad H. Nassralla, Naeem Akl, Zaher Dawy
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Distributed optimization
diffusion strategy
gradient descent
heterogeneous networks
Newton’s method
stochastic gradient descent
Online Access:https://ieeexplore.ieee.org/document/10255708/

Internet

https://ieeexplore.ieee.org/document/10255708/

Similar Items