Learned Trimmed-Ridge Regression for Channel Estimation in Millimeter-Wave Massive MIMO

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Pengxia, Cheng, Julian, Eldar, Yonina C., Cioffi, John M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929450737729536
author Wu, Pengxia
Cheng, Julian
Eldar, Yonina C.
Cioffi, John M.
author_facet Wu, Pengxia
Cheng, Julian
Eldar, Yonina C.
Cioffi, John M.
contents Channel estimation poses significant challenges in millimeter-wave massive multiple-input multiple-output systems, especially when the base station has fewer radio-frequency chains than antennas. To address this challenge, one promising solution exploits the beamspace channel sparsity to reconstruct full-dimensional channels from incomplete measurements. This paper presents a model-based deep learning method to reconstruct sparse, as well as approximately sparse, vectors fast and accurately. To implement this method, we propose a trimmed-ridge regression that transforms the sparse-reconstruction problem into a least-squares problem regularized by a nonconvex penalty term, and then derive an iterative solution. We then unfold the iterations into a deep network that can be implemented in online applications to realize real-time computations. To this end, an unfolded trimmed-ridge regression model is constructed using a structural configuration to reduce computational complexity and a model ensemble strategy to improve accuracy. Compared with other state-of-the-art deep learning models, the proposed learning scheme achieves better accuracy and supports higher downlink sum rates.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02934
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learned Trimmed-Ridge Regression for Channel Estimation in Millimeter-Wave Massive MIMO
Wu, Pengxia
Cheng, Julian
Eldar, Yonina C.
Cioffi, John M.
Information Theory
Signal Processing
Channel estimation poses significant challenges in millimeter-wave massive multiple-input multiple-output systems, especially when the base station has fewer radio-frequency chains than antennas. To address this challenge, one promising solution exploits the beamspace channel sparsity to reconstruct full-dimensional channels from incomplete measurements. This paper presents a model-based deep learning method to reconstruct sparse, as well as approximately sparse, vectors fast and accurately. To implement this method, we propose a trimmed-ridge regression that transforms the sparse-reconstruction problem into a least-squares problem regularized by a nonconvex penalty term, and then derive an iterative solution. We then unfold the iterations into a deep network that can be implemented in online applications to realize real-time computations. To this end, an unfolded trimmed-ridge regression model is constructed using a structural configuration to reduce computational complexity and a model ensemble strategy to improve accuracy. Compared with other state-of-the-art deep learning models, the proposed learning scheme achieves better accuracy and supports higher downlink sum rates.
title Learned Trimmed-Ridge Regression for Channel Estimation in Millimeter-Wave Massive MIMO
topic Information Theory
Signal Processing
url https://arxiv.org/abs/2408.02934