A CRITICAL LOOK AT RECENT TRENDS IN COMPRESSION OF CHANNEL STATE INFORMATION

In this paper, we challenge the current view on state-of-the-art deep learning-based methods for compressing wireless channel state information and show that traditional methods can be highly competitive on commonly used open-source benchmarks. We show that basic signal processing methods can offer superior performance and argue that the datasets and the metrics used in measuring performance give a skewed impression of the applicability and extendibility of the methods proposed in the literature today.