.png){kind=icon}
.png){kind=icon}
Return
Improved GPR-Based CSI Acquisition via Spatial-Correlation Kernel
.png){kind=icon}
OA
AI
DOI：10.1109/lwc.2026.3704829.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate channel estimation with low pilot overhead and computational complexity is key to efficiently utilizing multi-antenna wireless systems. Motivated by the evolution from purely statistical descriptions toward physics- and geometry-aware propagation models, this work focuses on incorporating channel information into a Gaussian process regression (GPR) framework for improving the channel estimation accuracy. In this work, we propose a GPR-based channel estimation framework along with a novel Spatial-Correlation (SC) kernel that explicitly captures the channel’s second-order statistics. We derive a closed-form expression of the proposed SC-based GPR estimator and prove that its posterior mean is optimal in terms of linear minimum mean-square error (LMMSE) under the same second-order statistics, without requiring the underlying channel distribution to be Gaussian. Our analysis reveals that, even with a 50% pilot overhead reduction, the proposed method achieves the lowest normalized mean-square error, competitive empirical 95% credible-interval coverage, and superior preservation of spectral efficiency compared to benchmark estimators, while maintaining lower computational complexity than the conventional LMMSE estimator.
Keywords:
6G
Gaussian process regression
MIMO channel estimation
pilot reduction
spatial-correlation
Journal
I
IF:
5.5
Papers:
682
Citations:
0