Deepcode and Modulo-SK are Designed for Different Settings
This clarifies misunderstandings in communication scheme comparisons, which is important for researchers in coding theory and feedback systems, though it is incremental as it corrects prior claims rather than introducing new methods.
The authors refute a claim that Modulo-SK outperforms Deepcode, demonstrating that the two schemes are designed for different settings (e.g., AWGN channel with uncoded vs. coded feedback). They also show that Deepcode dominates the optimized performance of SK in noisy feedback scenarios.
We respond to [1] which claimed that "Modulo-SK scheme outperforms Deepcode [2]". We demonstrate that this statement is not true: the two schemes are designed and evaluated for entirely different settings. DeepCode is designed and evaluated for the AWGN channel with (potentially delayed) uncoded output feedback. Modulo-SK is evaluated on the AWGN channel with coded feedback and unit delay. [1] also claimed an implementation of Schalkwijk and Kailath (SK) [3] which was numerically stable for any number of information bits and iterations. However, we observe that while their implementation does marginally improve over ours, it also suffers from a fundamental issue with precision. Finally, we show that Deepcode dominates the optimized performance of SK, over a natural choice of parameterizations when the feedback is noisy.