CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family
CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family
复制标题
DOI：
10.48550/arxiv.2210.00313
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Ashwin Hebbar;Viraj Nadkarni;Ashok Vardhan Makkuva;S. Bhat;Sewoong Oh;P. Viswanath
中科院分区：
文献类型：
--
作者：
Ashwin Hebbar;Viraj Nadkarni;Ashok Vardhan Makkuva;S. Bhat;Sewoong Oh;P. Viswanath
极化码是用于可靠通信的广泛使用的最先进的码，其最近被包括在第五代无线标准（5G）中。然而，对于在短块长度机制中既高效又可靠的极化解码器的设计仍然存在空间。受数据驱动通道解码器最近取得的成功的启发，我们引入了一种新型的基于$\textbf{C}$ur$\textbf{RI}$culum的$\textbf{S}$序列神经解码器，用于$\textbf{P}$olar码（CRISP）。我们设计了一个原则性的课程，以信息理论的见解为指导，训练CRISP，并表明它优于连续消除（SC）解码器，并在Polar（32，16）和Polar（64，22）码上达到接近最佳的可靠性性能。正如我们通过与其他课程进行比较所表明的那样，拟议课程的选择对于实现CRISP的准确性至关重要。更值得注意的是，CRISP可以容易地扩展到极化调整卷积（PAC）码，其中现有的SC解码器的可靠性明显较低。据我们所知，CRISP构造了第一个PAC码的数据驱动解码器，并在PAC（32，16）码上获得了接近最佳的性能。
Polar codes are widely used state-of-the-art codes for reliable communication that have recently been included in the 5th generation wireless standards (5G). However, there remains room for the design of polar decoders that are both efficient and reliable in the short blocklength regime. Motivated by recent successes of data-driven channel decoders, we introduce a novel $\textbf{C}$ur$\textbf{RI}$culum based $\textbf{S}$equential neural decoder for $\textbf{P}$olar codes (CRISP). We design a principled curriculum, guided by information-theoretic insights, to train CRISP and show that it outperforms the successive-cancellation (SC) decoder and attains near-optimal reliability performance on the Polar(32,16) and Polar(64,22) codes. The choice of the proposed curriculum is critical in achieving the accuracy gains of CRISP, as we show by comparing against other curricula. More notably, CRISP can be readily extended to Polarization-Adjusted-Convolutional (PAC) codes, where existing SC decoders are significantly less reliable. To the best of our knowledge, CRISP constructs the first data-driven decoder for PAC codes and attains near-optimal performance on the PAC(32,16) code.