ZeroCode：基于零矩阵通过强化学习按需构造纠错码
ZeroCode: On-demand Error-Correcting Code Construction from the Zero Matrix via Reinforcement Learning
浏览论文内容
中文总结 AI 辅助
ZeroCode提出一种基于强化学习的纠错码构造方法，从零矩阵顺序构建奇偶校验矩阵，通过动作掩蔽满足按需结构约束，在(32,16)码上较现有方法获得约1dB增益，并支持性能与复杂度权衡。
中文摘要 AI 辅助
纠错码（ECC）在从无线通信、存储到量子计算等众多应用中至关重要，然而每个应用都对奇偶校验矩阵（PCM）提出了不同的设计要求。为了在统一框架中满足这些按需需求，我们提出了ZeroCode，一种基于强化学习（RL）的方法，该方法从全零矩阵出发顺序构造PCM。ZeroCode将构造过程形式化为一个离散的序列决策问题，并使用带动作掩蔽的近端策略优化来选择有效边。在比特错误率（BER）为$10^{-4}$时，对于(32,16)码，ZeroCode相比先前基于RL的构造方法获得了约1 dB的增益，并且在我们的实验中优于现有的遗传算法、可微方法和经典码设计方法。除了优化解码性能外，掩蔽机制还允许灵活地加入按需结构约束，例如最大度数、无四环结构和准循环结构。此外，单次策略展开即可生成具有不同边数的PCM库，无需重新训练即可在解码性能与复杂度之间进行权衡。总体而言，ZeroCode在统一框架内解决了多样化的码设计需求，在给定约束下提供了具有优化解码性能的解决方案。
英文摘要
Error-correcting codes (ECCs) are essential across diverse applications, from wireless communications and storage to quantum computing, yet each application imposes distinct design requirements on the parity-check matrix (PCM). To address these on-demand requirements in a unified framework, we propose ZeroCode, a reinforcement learning (RL)-based approach that constructs PCMs sequentially from the all-zero matrix. ZeroCode formulates construction as a discrete sequential decision-making problem and uses proximal policy optimization with action masking to select valid edges. ZeroCode achieves a gain of approximately 1 dB over the prior RL-based construction method at a bit error rate (BER) of $10^{-4}$ for the (32,16) code and outperforms existing genetic, differentiable, and classical code-design methods in our experiments. Beyond optimizing decoding performance, the masking mechanism allows on-demand structural constraints, such as a maximum degree, 4-cycle-free structure, and quasi-cyclic structure, to be flexibly incorporated. Moreover, a single policy rollout yields a library of PCMs with varying edge counts, offering trade-offs between decoding performance and complexity without retraining. Overall, ZeroCode addresses diverse code-design requirements within a unified framework, providing solutions with optimized decoding performance under given constraints.
发表机构
- University of Ulsan（蔚山大学）
- Pohang University of Science and Technology (POSTECH)（浦项科技大学）
- Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
