Reproduce “EqDeepRx: Learning a Scalable and Interference Mitigating MIMO Receiver” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Mikko Honkala, Dani Korpi, Elias Raninen, Janne M. J. Huttunen
EqDeepRx combines conventional channel estimation and equalization with learned channel-estimate denoising and a shared-weight detector applied separately to each MIMO layer. Its parallel LMMSE and RZF equalizers provide complementary inputs to the detector. In CDL-C simulations with 10–15 m/s users, inter-cell interference, and data-rate-matched pilot settings, it needs about 2 dB less SINR than the conventional receiver at 10% BLER.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.