UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach

Mohammad, A; Masouros, C; Andreopoulos, Y; (2022) Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach. In: 2022 IEEE Wireless Communications and Networking Conference (WCNC). (pp. pp. 429-434). IEEE: Austin, TX, USA. Green open access

[thumbnail of 2111.08110v1.pdf]
Preview
PDF
2111.08110v1.pdf - Accepted Version

Download (838kB) | Preview

Abstract

Symbol level precoding (SLP) has been proven to be an effective means of managing the interference in a multiuser downlink transmission and also enhancing the received signal power. This paper proposes an unsupervised-learning based SLP that applies to quantized deep neural networks (DNNs). Rather than simply training a DNN in a supervised mode, our proposal unfolds a power minimization SLP formulation in an imperfect channel scenario using the interior point method (IPM) proximal 'log' barrier function. We use binary and ternary quantizations to compress the DNN's weight values. The results show significant memory savings for our proposals compared to the existing full-precision SLP-DNet with significant model compression of ~ 21× and ~ 13× for both binary DNN-based SLP (RSLP-BDNet) and ternary DNN-based SLP (RSLP-TDNets), respectively.

Type: Proceedings paper
Title: Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach
Event: 2022 IEEE Wireless Communications and Networking Conference (WCNC)
Dates: 10 Apr 2022 - 13 Apr 2022
ISBN-13: 9781665442664
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/WCNC51071.2022.9771799
Publisher version: https://doi.org/10.1109/WCNC51071.2022.9771799
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Training, Tensors, Quantization (signal), Precoding, Symbols, Minimization, Downlink
UCL classification: UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10152966
Downloads since deposit
25Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item