English

Neural Augmentation of MIMO-OFDM Receivers for Universal LLR Reconstruction

Signal Processing 2026-06-28 v1 Information Theory

Abstract

The growing demands for higher throughput and cost-efficient wireless communications drive the need for receivers that are both simple to deploy and robust to hardware impairments and nonlinear environments. While classical model-based receivers and recently proposed deep neural network ( DNN) architectures provide complementary benefits, they either rely on simplified linear Gaussian assumptions, require considerable computational resources, or are tailored for a given setting and modulation. In this work, we propose a compact and modular DNN augmentation that universally refines the soft outputs of existing receivers (model-based or data-driven), addressing two distinct operating regimes: structurally incomplete soft information arising from reduced-complexity detectors, and degraded soft outputs caused by hardware impairments and synchronization errors. A key property of the proposed framework is its task-agnostic nature: operating without any knowledge of the specific source of unreliability, it produces well-calibrated log-likelihood ratios (LLRs) suitable for channel decoding. Our design leverages an element-wise scaled convolutional neural network tailored to perform learned interference cancellation across users and neighboring subcarriers, combined with a training algorithm that encourages accurate LLR s for soft channel decoding. Numerical results demonstrate that the proposed augmentation consistently improves diverse receiver algorithms in challenging channel conditions while incurring minimal overhead.

Keywords

Cite

@article{arxiv.2606.29345,
  title  = {Neural Augmentation of MIMO-OFDM Receivers for Universal LLR Reconstruction},
  author = {Ory Eger and Nir Shlezinger},
  journal= {arXiv preprint arXiv:2606.29345},
  year   = {2026}
}

Comments

Under review for publication in the IEEE