Imperial College London
Portrait Picture

DrStefanVlaski

Faculty of Engineering, Department of Electrical and Electronic Engineering

Lecturer
 
 
 
//

Contact

 

s.vlaski

 
 
//

Location

 

810Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Sayed:2021:10.1109/ssp49050.2021.9513819,
author = {Sayed, AH and Vlaski, S},
doi = {10.1109/ssp49050.2021.9513819},
pages = {71--75},
publisher = {IEEE},
title = {Competing adaptive networks},
url = {http://dx.doi.org/10.1109/ssp49050.2021.9513819},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Adaptive networks have the capability to pursue solutions of global stochastic optimization problems by relying only local interactions within neighborhoods. The diffusion of information through repeated interactions allows for globally optimal behavior, without the need for central coordination. Most existing strategies are developed for cooperative learning settings, where the objective of the network is common to all agents. We consider in this work a team setting, where a subset of the agents form a team with a common goal, while competing with the remainder of the network. We develop an algorithm for decentralized competition among teams of adaptive agents, analyze its dynamics and present an application in the decentralized training of generative adversarial neural networks.
AU  - Sayed,AH
AU  - Vlaski,S
DO  - 10.1109/ssp49050.2021.9513819
EP  - 75
PB  - IEEE
PY  - 2021///
SP  - 71
TI  - Competing adaptive networks
UR  - http://dx.doi.org/10.1109/ssp49050.2021.9513819
UR  - http://hdl.handle.net/10044/1/111100
ER  -
Download