用于 QLDPC 码可扩展解码的机器学习消息传递
Machine Learning Message-Passing for the Scalable Decoding of QLDPC Codes
AI总结:
提出基于图神经网络的可扩展解码器 Astra,通过机器学习消息传递替代传统置信传播与 OSD 后处理,在表面码和 BB 码上实现更低逻辑错误率与更高阈值,并支持跨距离外推解码。
摘要:
我们提出了 Astra,一种使用图神经网络的新型可扩展解码器。我们的解码器工作原理类似于求解由 Tanner 图表示的约束数独谜题。通常,量子低密度奇偶校验(QLDPC)解码基于置信传播(BP,消息传递的一种变体),并且需要耗时的后处理方法,如有序统计解码(OSD)。在不使用任何后处理的情况下,与 BP+OSD 相比,Astra 实现了更高的阈值和更好的逻辑错误率,这适用于训练至距离 11 的表面码和训练至距离 18 的双变量自行车(BB)码。此外,我们可以成功外推解码功能:通过使用在较低距离上训练的解码器,我们能够解码高距离(表面码最高至距离 25,BB 码最高至距离 34)。Astra+OSD 比 BP+OSD 更快。我们表明,随着物理错误率的降低,与 BP+OSD 相比,Astra+OSD 对 OSD 的调用次数逐渐减少,即使在外推解码的情况下也是如此。与 BP(+OSD) 相比,Astra(+OSD) 在 BB 码上实现了数量级更低的逻辑错误率。源代码已在 \url{https://github.com/arshpreetmaan/astra} 开源。
英文摘要:
We present Astra, a novel and scalable decoder using graph neural networks. Our decoder works similarly to solving a Sudoku puzzle of constraints represented by the Tanner graph. In general, Quantum Low Density Parity Check (QLDPC) decoding is based on Belief Propagation (BP, a variant of message-passing) and requires time intensive post-processing methods such as Ordered Statistics Decoding (OSD). Without using any post-processing, Astra achieves higher thresholds and better logical error rates when compared to BP+OSD, both for surface codes trained up to distance 11 and Bivariate Bicycle (BB) codes trained up to distance 18. Moreover, we can successfully extrapolate the decoding functionality: we decode high distances (surface code up to distance 25 and BB code up to distance 34) by using decoders trained on lower distances. Astra+OSD is faster than BP+OSD. We show that with decreasing physical error rates, Astra+OSD makes progressively fewer calls to OSD when compared to BP+OSD, even in the context of extrapolated decoding. Astra(+OSD) achieves orders of magnitude lower logical error rates for BB codes compared to BP(+OSD). The source code is open-sourced at \url{https://github.com/arshpreetmaan/astra}.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。