Ray-Tracing-Parameter-Based Lightweight Hybrid Precoding via Cascade XGBoost for Wideband Massive MIMO-OFDM Systems
Abstract
Hybrid precoding reduces the radio-frequency (RF) hardware burden in wideband massive MIMO-OFDM systems, but conventional optimization and deep neural network (DNN)-based approaches can incur high online complexity. This paper proposes XGB-SVD, a lightweight hybrid precoding framework that maps compact ray-tracing path parameters directly to analog beamforming codeword indices using cascade eXtreme Gradient Boosting (XGBoost). The cascade captures sequential beam-selection dependencies and transmit--receive propagation correlation, while the digital precoder and combiner are obtained from the reduced-dimensional equivalent channel using singular value decomposition (SVD). Evaluations over five DeepMIMO scenarios spanning sub-6-GHz and millimeter-wave bands show that XGB-SVD consistently outperforms the considered DNN baselines and approaches simultaneous orthogonal matching pursuit (SOMP) in several environments. Cross-scenario results further indicate improved transfer from propagation-diverse training environments, while XGB-SVD provides lower online computational and training costs than the DNN baselines.
Related
- Reduced-Feedback Hybrid Precoding for Wideband mmWave MIMO-OFDM Systems via Hierarchical Interpolation
- MAP-Based Task-Oriented Precoding for Multiuser Communication
- Joint Quantized Precoding and Bit Allocation for Fronthaul-Constrained Cell-Free Massive MIMO
- Hamiltonian Monte Carlo for Vector Perturbation Precoding in MU-MIMO via Continuous Relaxation
- Low-Complexity SVD-Based Precoding over Zero-Padded ISI Channels
BibTeX
@misc{chou2026raytracingparameterbased,
title = {{Ray-Tracing-Parameter-Based Lightweight Hybrid Precoding via Cascade XGBoost for Wideband Massive MIMO-OFDM Systems}},
author = {Po-Heng Chou and Wei-Chen Lin and Wan-Jen Huang and Walid Saad and Ronald Y. Chang},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01880},
eprint = {2611.01880},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01880},
}
RIS
TY - UNPB
TI - Ray-Tracing-Parameter-Based Lightweight Hybrid Precoding via Cascade XGBoost for Wideband Massive MIMO-OFDM Systems
AU - Po-Heng Chou
AU - Wei-Chen Lin
AU - Wan-Jen Huang
AU - Walid Saad
AU - Ronald Y. Chang
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01880
UR - https://arxiv.org/abs/2611.01880
AB - Hybrid precoding reduces the radio-frequency (RF) hardware burden in wideband massive MIMO-OFDM systems, but conventional optimization and deep neural network (DNN)-based approaches can incur high online complexity. This paper proposes XGB-SVD, a lightweight hybrid precoding framework that maps compact ray-tracing path parameters directly to analog beamforming codeword indices using cascade eXtreme Gradient Boosting (XGBoost). The cascade captures sequential beam-selection dependencies and transmit--receive propagation correlation, while the digital precoder and combiner are obtained from the reduced-dimensional equivalent channel using singular value decomposition (SVD). Evaluations over five DeepMIMO scenarios spanning sub-6-GHz and millimeter-wave bands show that XGB-SVD consistently outperforms the considered DNN baselines and approaches simultaneous orthogonal matching pursuit (SOMP) in several environments. Cross-scenario results further indicate improved transfer from propagation-diverse training environments, while XGB-SVD provides lower online computational and training costs than the DNN baselines.
ER -