🤖 AI Summary
This paper addresses robust multi-user multiple-input multiple-output (MU-MIMO) beamforming under imperfect and statistically unknown channel state information (CSI) errors. Method: We propose a hybrid “offline learning + online adaptation” framework: (i) a shared deep neural network implicitly models the error covariance structure, eliminating reliance on prior statistical assumptions; (ii) a sparse-augmented low-rank (SALR) architecture reduces computational complexity; and (iii) a multi-base model-agnostic meta-learning (MB-MAML) strategy enables dynamic optimal initialization and rapid online gradient fine-tuning. Contribution/Results: The proposed method significantly outperforms state-of-the-art approaches under unknown and non-stationary channel conditions. It achieves strong cross-channel generalization, high robustness against CSI uncertainty, and low online computational overhead—demonstrating superior practicality for real-world deployment.
📝 Abstract
Robust beamforming design under imperfect channel state information (CSI) is a fundamental challenge in multiuser multiple-input multiple-output (MU-MIMO) systems, particularly when the channel estimation error statistics are unknown. Conventional model-driven methods usually rely on prior knowledge of the error covariance matrix and data-driven deep learning approaches suffer from poor generalization capability to unseen channel conditions. To address these limitations, this paper proposes a hybrid offline-online framework that achieves effective offline learning and rapid online adaptation. In the offline phase, we propose a shared (among users) deep neural network (DNN) that is able to learn the channel estimation error covariance from observed samples, thus enabling robust beamforming without statistical priors. Meanwhile, to facilitate real-time deployment, we propose a sparse augmented low-rank (SALR) method to reduce complexity while maintaining comparable performance. In the online phase, we show that the proposed network can be rapidly fine-tuned with minimal gradient steps. Furthermore, a multiple basis model-agnostic meta-learning (MB-MAML) strategy is further proposed to maintain multiple meta-initializations and by dynamically selecting the best one online, we can improve the adaptation and generalization capability of the proposed framework under unseen or non-stationary channels. Simulation results demonstrate that the proposed offline-online framework exhibits strong robustness across diverse channel conditions and it is able to significantly outperform state-of-the-art (SOTA) baselines.