End-to-end autoencoder (AE) learning has the potential of exceeding the performance of human-engineered transceivers and encoding schemes, without a priori knowledge of communication-theoretic principles. In this work, we aim to understand to what extent and for which scenarios this claim holds true when comparing with fair benchmarks. Our particular focus is on memoryless multiple-input multiple-output (MIMO) and multi-user (MU) systems. Four case studies are considered: two point-to-point (closed-loop and open-loop MIMO) and two MU scenarios (MIMO broadcast and interference channels). For the point-to-point scenarios, we explain some of the performance gains observed in prior work through the selection of improved baseline schemes that include geometric shaping as well as bit and power allocation. For the MIMO broadcast channel, we demonstrate the feasibility of a novel AE method with centralized learning and decentralized execution. Interestingly, the learned scheme performs close to nonlinear vector-perturbation precoding and significantly outperforms conventional zero-forcing. Lastly, we highlight potential pitfalls when interpreting learned communication schemes. In particular, we show that the AE for the considered interference channel learns to avoid interference, albeit in a rotated reference frame. After de-rotating the learned signal constellation of each user, the resulting scheme corresponds to conventional time sharing with geometric shaping.

中文翻译：

---

MIMO 和多用户通信的端到端学习的基准测试和解释


端到端自动编码器（AE）学习有可能超越人工设计的收发器和编码方案的性能，而无需先验通信理论原理的知识。在这项工作中，我们的目标是了解在与公平基准进行比较时，这种说法在多大程度上以及在哪些场景下是正确的。我们特别关注无记忆多输入多输出 (MIMO) 和多用户 (MU) 系统。考虑了四个案例研究：两个点对点（闭环和开环 MIMO）和两个 MU 场景（MIMO 广播和干扰信道）。对于点对点场景，我们解释了通过选择改进的基线方案（包括几何整形以及比特和功率分配）在之前的工作中观察到的一些性能增益。对于 MIMO 广播信道，我们展示了一种具有集中学习和分散执行的新型 AE 方法的可行性。有趣的是，学习方案的性能接近非线性矢量扰动预编码，并且显着优于传统的迫零。最后，我们强调了解释学习到的通信方案时的潜在陷阱。特别是，我们表明，所考虑的干扰信道的 AE 学会了避免干扰，尽管是在旋转的参考系中。在对每个用户的学习信号星座进行去旋转之后，得到的方案对应于具有几何整形的传统时间共享。