This letter proposes a learning aided gradient descent (LAGD) algorithm to solve the weighted sum rate (WSR) maximization problem for multiple-input single-output (MISO) beamforming. The proposed LAGD algorithm directly optimizes the transmit precoder through implicit gradient descent based iterations, at each of which the optimization strategy is determined by a neural network, and thus, is dynamic and adaptive. At each instance of the problem, this network is initialized randomly, and updated throughout the iterative solution process. Therefore, the LAGD algorithm can be implemented at any signal-to-noise ratio (SNR) and for arbitrary antenna/user numbers, does not require labelled data or training prior to deployment. Numerical results show that the LAGD algorithm can outperform of the well-known WMMSE algorithm as well as other learning-based solutions with a modest computational complexity. Our code is available at https://github.com/XiaGroup/LAGD.

A Learning Aided Flexible Gradient Descent Approach to MISO Beamforming / Yang, Z.; Xia, J.; Luo, J.; Zhang, S.; Gunduz, D.. - In: IEEE WIRELESS COMMUNICATIONS LETTERS. - ISSN 2162-2337. - 11:9(2022), pp. 1895-1899. [10.1109/LWC.2022.3186160]

A Learning Aided Flexible Gradient Descent Approach to MISO Beamforming

Zhang S.;Gunduz D.
2022

Abstract

This letter proposes a learning aided gradient descent (LAGD) algorithm to solve the weighted sum rate (WSR) maximization problem for multiple-input single-output (MISO) beamforming. The proposed LAGD algorithm directly optimizes the transmit precoder through implicit gradient descent based iterations, at each of which the optimization strategy is determined by a neural network, and thus, is dynamic and adaptive. At each instance of the problem, this network is initialized randomly, and updated throughout the iterative solution process. Therefore, the LAGD algorithm can be implemented at any signal-to-noise ratio (SNR) and for arbitrary antenna/user numbers, does not require labelled data or training prior to deployment. Numerical results show that the LAGD algorithm can outperform of the well-known WMMSE algorithm as well as other learning-based solutions with a modest computational complexity. Our code is available at https://github.com/XiaGroup/LAGD.
2022
11
9
1895
1899
A Learning Aided Flexible Gradient Descent Approach to MISO Beamforming / Yang, Z.; Xia, J.; Luo, J.; Zhang, S.; Gunduz, D.. - In: IEEE WIRELESS COMMUNICATIONS LETTERS. - ISSN 2162-2337. - 11:9(2022), pp. 1895-1899. [10.1109/LWC.2022.3186160]
Yang, Z.; Xia, J.; Luo, J.; Zhang, S.; Gunduz, D.
File in questo prodotto:
File Dimensione Formato  
A_Learning_Aided_Flexible_Gradient_Descent_Approach_to_MISO_Beamforming.pdf

Accesso riservato

Tipologia: Versione pubblicata dall'editore
Dimensione 2.49 MB
Formato Adobe PDF
2.49 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
2206.10499.pdf

embargo fino al 09/09/2024

Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 2.41 MB
Formato Adobe PDF
2.41 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1286025
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 3
social impact