A Learnable Optimization and Regularization Approach to Massive MIMO CSI Feedback

TL;DR

This paper introduces LORA, a deep learning-based method for efficient and accurate CSI feedback in massive MIMO systems, utilizing learnable regularization and quantization to adapt to different feedback bit rates.

Contribution

The paper proposes a novel model-driven deep learning approach, LORA, that replaces fixed regularization with learnable modules and unfolds an iterative algorithm into a neural network for improved CSI feedback.

Findings

LORA enhances CSI feedback accuracy and speed.

It operates effectively across various bit rates.

The method demonstrates robustness in realistic scenarios.

Abstract

Channel state information (CSI) plays a critical role in achieving the potential benefits of massive multiple input multiple output (MIMO) systems. In frequency division duplex (FDD) massive MIMO systems, the base station (BS) relies on sustained and accurate CSI feedback from the users. However, due to the large number of antennas and users being served in massive MIMO systems, feedback overhead can become a bottleneck. In this paper, we propose a model-driven deep learning method for CSI feedback, called learnable optimization and regularization algorithm (LORA). Instead of using l1-norm as the regularization term, a learnable regularization module is introduced in LORA to automatically adapt to the characteristics of CSI. We unfold the conventional iterative shrinkage-thresholding algorithm (ISTA) to a neural network and learn both the optimization process and regularization term by end-toend training. We show that LORA improves the CSI feedback accuracy and speed. Besides, a novel learnable quantization method and the corresponding training scheme are proposed, and it is shown that LORA can operate successfully at different bit rates, providing flexibility in terms of the CSI feedback overhead. Various realistic scenarios are considered to demonstrate the effectiveness and robustness of LORA through numerical simulations.