This paper considers a transmitter, which uses random linear coding (RLC) to encode data packets. The generated coded packets are broadcast to one or more receivers. A receiver can recover the data packets if it gathers a sufficient number of coded packets. We assume that the receiver does not abandon its efforts to recover the data packets if RLC decoding has been unsuccessful; instead, it employs syndrome decoding in an effort to repair erroneously received coded packets before it attempts RLC decoding again. A key assumption of most decoding techniques, including syndrome decoding, is that errors are independently and identically distributed within the received coded packets. Motivated by the `guessing random additive noise decoding' (GRAND) framework, we develop transversal GRAND: an algorithm that exploits statistical dependence in the occurrence of errors, complements RLC decoding and achieves a gain over syndrome decoding, in terms of the probability that the receiver will recover the original data packets.
翻译:本文考虑的是使用随机线性编码( RLC)来编码数据包的发报机。 生成的编码包将广播给一个或多个接收器。 如果接收器收集到足够数量的编码包, 接收器可以回收数据包。 我们假设接收器不会放弃在RLC解码失败时恢复数据包的努力; 相反, 它使用综合解码来努力修复错误收到的编码包, 然后再尝试 RLC解码。 大多数解码技术, 包括综合解码的关键假设是错误在接收的编码包中独立和同样地分布。 受“ 猜测随机添加噪音解码” (GRAND) 框架的驱动, 我们开发了横向GRAND: 一种算法,在错误发生时利用统计依赖性, 补充RLC解码, 并实现综合解码的收益, 即接收器将恢复原始数据包的概率。