This paper studies the problem of linear precoding for multiple-input multiple-output (MIMO) communication channels employing finite-alphabet signaling. Existing solutions typically suffer from high computational complexity due to costly computations of the constellation-constrained mutual information. In contrast to existing works, this paper takes a different path of tackling the MIMO precoding problem. Namely, a data-driven approach, based on deep learning, is proposed. In the offline training phase, a deep neural network learns the optimal solution on a set of MIMO channel matrices. This allows the reduction of the computational complexity of the precoder optimization in the online inference phase. Numerical results demonstrate the efficiency of the proposed solution vis-à-vis existing precoding algorithms in terms of significantly reduced complexity and close-to-optimal performance.

本文研究了采用有限字母表信令的多输入多输出 (MIMO) 通信信道的线性预编码问题。由于星座约束互信息的昂贵计算，现有解决方案通常遭受高计算复杂性。与现有工作相比，本文采用了不同的路径来解决 MIMO 预编码问题。即，提出了一种基于深度学习的数据驱动方法。在离线训练阶段，深度神经网络在一组 MIMO 信道矩阵上学习最优解。这允许降低在线推理阶段预编码器优化的计算复杂度。