Neural Augmentation of MIMO-OFDM Receivers for Universal LLR Reconstruction

2026-06-28

AI Summary

This work addresses the significant degradation in decoding performance caused by inaccurate log-likelihood ratios (LLRs) generated by practical MIMO-OFDM receivers under hardware impairments, synchronization errors, or simplified architectures. To overcome this limitation, the authors propose a lightweight, modular deep neural network post-processing framework capable of universally refining soft information from diverse non-ideal receivers without requiring explicit knowledge of the distortion sources. The method employs an element-wise scaled convolutional network that jointly learns interference across users and subcarriers, combined with a soft-decoding-oriented training strategy to optimize LLR calibration. Experimental results demonstrate that the proposed approach substantially improves bit error rate performance across various complex channel conditions while introducing minimal computational and deployment overhead.

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.

Problem

• MIMO-OFDM
• log-likelihood ratios
• hardware impairments
• soft information
• receiver robustness

Innovation

• neural augmentation
• universal LLR reconstruction
• MIMO-OFDM receivers
• task-agnostic DNN
• learned interference cancellation