Benchmarking and Interpreting End-to-end Learning of MIMO and Multi-User Communication
Artikel i vetenskaplig tidskrift, 2022

End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. Our particular focus is on memoryless multiple-input multiple-output (MIMO) and multi-user (MU) systems. Four case studies are considered: two point-to-point (closed-loop and open-loop MIMO) and two MU scenarios (MIMO broadcast and interference channels). For the point-to-point scenarios, we explain some of the performance gains observed in prior work through the selection of improved baseline schemes that include geometric shaping as well as bit and power allocation. For the MIMO broadcast channel, we demonstrate the feasibility of a novel AE method with centralized learning and decentralized execution. Interestingly, the learned scheme performs close to nonlinear vector-perturbation precoding and significantly outperforms conventional zero-forcing. Lastly, we highlight potential pitfalls when interpreting learned communication schemes. In particular, we show that the AE for the considered interference channel learns to avoid interference, albeit in a rotated reference frame. After de-rotating the learned signal constellation of each user, the resulting scheme corresponds to conventional time sharing with geometric shaping.

Wireless communication

MIMO broadcast

Receivers

machine learning

Benchmark testing

deep learning

end-to-end learning

wireless communications

interference channel

Transmitting antennas

digital signal processing

Training

Autoencoders

Interference channels

MIMO communication

Författare

Jinxiang Song

Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk

Christian Häger

Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk

Jochen Schröder

Chalmers, Mikroteknologi och nanovetenskap, Fotonik

Tim O'Shea

Virginia Polytechnic Institute and State University

Erik Agrell

Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk

Henk Wymeersch

Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk

IEEE Transactions on Wireless Communications

15361276 (ISSN) 15582248 (eISSN)

Vol. 21 9 7287-7298

Coding for terabit-per-second fiber-optical communications (TERA)

Europeiska kommissionen (EU) (EC/H2020/749798), 2017-01-01 -- 2019-12-31.

Frigöra full fiberoptisk kapacitet

Knut och Alice Wallenbergs Stiftelse (KAW 2018.0090), 2019-07-01 -- 2024-06-30.

Ämneskategorier

Telekommunikation

Kommunikationssystem

Signalbehandling

DOI

10.1109/TWC.2022.3157467

Mer information

Senast uppdaterat

2022-12-27