Imperial College London
Alternate

ProfessorKinLeung

Faculty of Engineering, Department of Electrical and Electronic Engineering

Tanaka Chair in Internet Technology
 
 
 
//

Contact

 

+44 (0)20 7594 6238kin.leung Website

 
 
//

Assistant

 

Miss Vanessa Rodriguez-Gonzalez +44 (0)20 7594 6267

 
//

Location

 

810aElectrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Chen:2021:10.1109/MILCOM52596.2021.9652922,
author = {Chen, Z and Leung, KK and Wang, S and Tassiulas, L and Chan, K},
doi = {10.1109/MILCOM52596.2021.9652922},
pages = {503--508},
publisher = {IEEE},
title = {Robust solutions to constrained optimization problems by LSTM networks},
url = {http://dx.doi.org/10.1109/MILCOM52596.2021.9652922},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Many technical issues for communications and computer infrastructures, including resource sharing, network management and distributed analytics, can be formulated as optimization problems. Gradient-based iterative algorithms have been widely utilized to solve these problems. Much research focuses on improving the iteration convergence. However, when system parameters change, it requires a new solution from the iterative methods. Therefore, it is helpful to develop machine-learning solution frameworks that can quickly produce solutions over a range of system parameters. We propose here a learning approach to solve non-convex, constrained optimization problems. Two coupled Long Short Term Memory (LSTM) networks are used to find the optimal solution. The advantages of this new framework include: (1) near optimal solution for a given problem instance can be obtained in very few iterations (time steps) during the inference process, (2) the learning approach allows selections of various hyper-parameters to achieve desirable tradeoffs between the training time and the solution quality, and (3) the coupled-LSTM networks can be trained using system parameters with distributions different from those used during inference to generate solutions, thus enhancing the robustness of the learning technique. Numerical experiments using a dataset from Alibaba reveal that the relative discrepancy between the generated solution and the optimum is less than 1% and 0.1% after 2 and 12 iterations, respectively.
AU  - Chen,Z
AU  - Leung,KK
AU  - Wang,S
AU  - Tassiulas,L
AU  - Chan,K
DO  - 10.1109/MILCOM52596.2021.9652922
EP  - 508
PB  - IEEE
PY  - 2021///
SN  - 2155-7578
SP  - 503
TI  - Robust solutions to constrained optimization problems by LSTM networks
UR  - http://dx.doi.org/10.1109/MILCOM52596.2021.9652922
UR  - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000819479500081&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
UR  - https://ieeexplore.ieee.org/abstract/document/9652922
UR  - http://hdl.handle.net/10044/1/101699
ER  -
Download