[论文] Learning-to-Transition for Large-scale and High-Order MIMO Detection

论文概要

研究领域: ML 作者: Yubo Zhang, Yiyao Liu, Xiaodong Wang 发布时间: 2026-08-17 arXiv: 2508.08539

中文摘要

高阶多输入多输出（MIMO）检测需要在大型离散符号空间上高效搜索，同时为信道解码生成可靠的软信息。本文提出一种学习转移（L2T）框架，将MIMO检测形式化为完整向量转移的随机序列。在每次转移中，信道耦合Transformer同时更新实例嵌入和采样策略，而块自回归分解以适度的序列复杂度捕捉流间依赖性。对于硬输出检测，转移网络被递归应用并通过残差到BER课程训练，首先从精确残差度量学习MIMO搜索几何，然后将策略与传输比特精度对齐。对于软输出接收，训练好的硬策略在参数层面被克隆到 untied 软输入软输出迭代检测解码（IDD）接收器的每一层。这种 tied-to-untied 迁移保留了学习到的零先验搜索动态，同时支持在解码器反馈下进行层和轮次特定的特化。在每个IDD轮次内，解码器先验根据贝叶斯规则倾斜候选生成，似然加权的终端假设为LDPC解码产生后验和外在对数似然比。多阶段训练策略通过逐步让接收器接触合成和环路内解码器生成的先验，进一步稳定了硬到软的迁移。

原文摘要

High-order multiple-input multiple-output (MIMO) detection requires efficient search over a large discrete symbol space while producing reliable soft information for channel decoding. This paper develops a learning-to-transition (L2T) framework that formulates MIMO detection as a stochastic sequence of complete-vector transitions. At each transition, a channel-coupled Transformer updates both the instance embedding and the sampling policy, while a blockwise autoregressive factorization captures inter-stream dependence with moderate sequential complexity. For hard-output detection, a transition network is applied recursively and trained through a residual-to-BER curriculum, which first learns the MIMO search geometry from the exact residual metric and then aligns the policy with transmitted…

— 自动采集于 2026-08-18

#论文 #arXiv #ML #小凯