Training channel selection for learning-based 1-bit precoding in massive MU-MIMO

Sitian Li, Andreas Burg, Alexios Balatsoukas-Stimming

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review


Learning-based algorithms have gained great popularity in communications since they often outperform even carefully engineered solutions by learning from training samples. In this paper, we show that the selection of appropriate training examples can be important for the performance of such learning-based algorithms. In particular, we consider non-linear 1-bit precoding for massive multi-user MIMO systems using the C2PO algorithm. While previous works have already shown the advantages of learning critical coefficients of this algorithm, we demonstrate that straightforward selection of training samples that follow the channel model distribution does not necessarily lead to the best result. Instead, we provide a strategy to generate training data based on the specific properties of the algorithm, which significantly improves its error floor performance.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Communications Workshops, ICC Workshops 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)978-1-7281-7440-2
Publication statusPublished - Jun 2020
Event2020 IEEE International Conference on Communications (ICC 2020) - Dublin, Ireland
Duration: 7 Jun 202011 Jun 2020


Conference2020 IEEE International Conference on Communications (ICC 2020)


  • 1-bit precoding
  • C2PO
  • Massive multi-user multiple-input multiple-output (MU-MIMO)
  • Neural network
  • Unfolded learning


Dive into the research topics of 'Training channel selection for learning-based 1-bit precoding in massive MU-MIMO'. Together they form a unique fingerprint.

Cite this