Even though machine learning (ML) techniques are being widely used in communications, the question of how to train communication systems has received surprisingly little attention. In this paper, we show that the commonly used binary cross-entropy (BCE) loss is a sensible choice in uncoded systems, e.g., for training ML-assisted data detectors, but may not be optimal in coded systems. We propose new loss functions targeted at minimizing the block error rate and SNR deweighting, a novel method that trains communication systems for optimal performance over a range of signal-to-noise ratios. The utility of the proposed loss functions as well as of SNR deweighting is shown through simulations in NVIDIA Sionna.

翻译：尽管机器学习（ML）技术正被广泛应用于通信领域，但关于如何训练通信系统这一问题却鲜少受到关注。本文表明，在未编码系统中（例如用于训练ML辅助数据检测器），常用的二元交叉熵（BCE）损失函数是合理的选择，但在编码系统中可能并非最优。我们提出了一种新的损失函数，旨在最小化块误码率与信噪比降权（SNR deweighting），这是一种通过在不同信噪比范围内实现最优性能来训练通信系统的新方法。通过NVIDIA Sionna平台的仿真，展示了所提出的损失函数以及信噪比降权方法的有效性。