English(EN) Joint End-to-End Training of Weighted BP Decoder Ensembles

新方法训练解码器集成模型以提高LDPC码的可靠性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-28 04:00

研究人员开发了一种新颖的方法，用于训练加权信念传播（BP）解码器集成模型，以提高低密度奇偶校验（LDPC）码的解码可靠性。该方法不依赖于特定码结构的差异性，而是通过联合优化可训练的Tanner图边权重来学习互补的解码行为。研究比较了四种集成目标，发现最佳成员训练是最有效的策略。对于（64,32）PEG LDPC码，在10^-4的帧错误率下，该方法比单个信念传播解码器实现了约0.66 dB的增益，证明了学习到的专业化和互补的失败事件，而不是统一改进的组件解码器。 AI

影响这项研究通过提高数据传输中的纠错能力，可能带来更强大的通信系统。

排序理由学术论文，详细介绍了训练AI相关算法的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了训练AI相关算法的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Felix Krieg, Paul Bezner, Stephan ten Brink · 2026-10-28 04:00

加权BP解码器集成模型的联合端到端训练

arXiv:2610.33559v1 Announce Type: cross Abstract: Ensemble decoding improves decoding reliability by combining component decoders with complementary failure events. Existing approaches typically obtain this diversity from code-specific structure, such as code automorphisms, multi…

本文如何被排名

报道来源 [1]

加权BP解码器集成模型的联合端到端训练

相关实体

相关话题