Distributed Over-the-Air Computing for Fast Distributed Optimization: Beamforming Design and Convergence Analysis

Zhenyi Lin1; Yi Gong1; Kaibin Huang2

2022

10.1109/JSAC.2022.3223661

IEEE Journal on Selected Areas in Communications   影响因子和分区

1558-0008

1558-0008

Distributed optimization finds a wide range of applications ranging from machine learning to vehicle platooning. To overcome the bottleneck caused by the required extensive message exchange, we propose in this work the framework of distributed over-the-air computing (AirComp) to realize a one-step aggregation for distributed optimization. Equivalently, the technique superimposes multiple instances of conventional AirComp processes, giving rise to the challenge of jointly designing multicast beamforming at devices to rein in errors due to interference and channel distortion. We consider two design criteria. One is to minimize the sum AirComp error (i.e., sum mean-squared error (MSE)) with respect to the desired average-functional values. An efficient solution approach is proposed by transforming the non-convex beamforming problem into an equivalent concave-convex fractional program and solving it by nesting convex programming into a bisection search. The other one, called zero-forcing (ZF) multicast beamforming, is to force the received over-the-air aggregated signals at devices to be equal to the desired functional values, where the optimal beamforming admits closed form. Last, the convergence of a classic distributed optimization algorithm is analyzed. The distributed AirComp is found experimentally to accelerate convergence by dramatically reducing communication latency.

Beamforming distributed networks over-the-air computation distributed optimization convergence analysis

SCI ; EI

英语

第一

National Key Research and Development Program of China[2019YFB1802800] ; National Natural Science Foundation of China[62071212] ; Guangdong Basic and Applied Basic Research Foundation[2019B1515130003] ; Research Grants Council of the Hong Kong Special Administrative Region[HKU RFS2122-7S04] ; Hong Kong Research Grants Council[17208319] ; Shenzhen Science and Technology Program[JCYJ20200109141414409]

Engineering ; Telecommunications

Engineering, Electrical & Electronic ; Telecommunications

WOS:000927934500018

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20225113271946

Array processing ; Artificial intelligence ; Convex optimization ; Distributed computer systems ; Errors ; Learning systems ; Mean square error ; Multicasting

Electromagnetic Waves in Relation to Various Structures:711.2 ; Telecommunication; Radar, Radio and Television:716 ; Optical Communication:717 ; Telephone Systems and Related Technologies; Line Communications:718 ; Digital Computers and Systems:722.4 ; Artificial Intelligence:723.4 ; Mathematical Statistics:922.2

COMPUTER SCIENCE

IEEE

1.Department of Electrical and Electronics Engineering, Southern University of Science and Technology, Shenzhen, China
2.Department of Electrical and Electronics Engineering, The University of Hong Kong, Hong Kong, China

Zhenyi Lin,Yi Gong,Kaibin Huang. Distributed Over-the-Air Computing for Fast Distributed Optimization: Beamforming Design and Convergence Analysis[J]. IEEE Journal on Selected Areas in Communications,2022,PP(99):1-1.

Zhenyi Lin,Yi Gong,&Kaibin Huang.(2022).Distributed Over-the-Air Computing for Fast Distributed Optimization: Beamforming Design and Convergence Analysis.IEEE Journal on Selected Areas in Communications,PP(99),1-1.

Zhenyi Lin,et al."Distributed Over-the-Air Computing for Fast Distributed Optimization: Beamforming Design and Convergence Analysis".IEEE Journal on Selected Areas in Communications PP.99(2022):1-1.