Abstract | ||
---|---|---|
End-to-end data-driven machine learning (ML) of multiple-input multiple-output (MIMO) systems has been shown to have the potential of exceeding the performance of engineered M IMO transceivers, without any 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. We study closed-loop MIMO, open-loop MIMO, and multi-user MIMO (MU-MIMO) and show that the gains of ML-based communication in the former two cases can be to a large extent ascribed to implicitly learned geometric shaping and bit and power allocation, not to learning new spatial encoders. For MU-MIMO, we demonstrate the feasibility of a novel method with centralized learning and decentralized executing, outperforming conventional zero-forcing. For each scenario, we provide explicit descriptions as well as open-source implementations of the selected neural-network architectures. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/GLOBECOM42002.2020.9322115 | 2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) |
DocType | ISSN | Citations |
Conference | 2334-0983 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Song Jinxiang | 1 | 0 | 0.34 |
Christian Häger | 2 | 1 | 3.06 |
jochen schroder | 3 | 1 | 4.01 |
O'Shea Tim | 4 | 0 | 0.34 |
Henk Wymeersch | 5 | 1589 | 128.47 |