发表机构
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出RAOA循环架构，利用可编程无线电传播实现交替算子计算，在离散优化和语言模型适配中验证了其有效性，连接了计算、传播与神经适配。
AI 中文摘要
可编程无线电传播能否作为计算深度而不仅仅作为通信信道或一次性模拟变换？我们提出了无线电交替算子拟设（RAOA），这是一种循环计算架构，在持久潜在状态上交替进行能量推导的问题更新与混合更新。在每次混合后重新计算问题场，使得即使跨深度重用相同的学习控制，重复传递也具有组合性。我们通过精确离散优化、受约束的可编程传播模拟以及预训练模型适配来评估这一想法。在离散目标上，重复执行可以在不增加学习控制数量的情况下提高解的质量，并且相同的公式可直接处理高阶交互。一个无源纯相位自由空间模型进一步表明，所需的算子可以通过可编程传播来近似，同时在存在实现误差的情况下保留有用的下游行为。当作为零初始化残差适配器插入时，RAOA在三个模型家族上适配预训练语言模型，其WikiText性能接近匹配的浅层MLP，而推理任务迁移仍依赖于模型。总之，这些结果在一个循环框架内连接了交替算子计算、可编程无线电传播和神经适配。射频实现证据基于模拟而非硬件演示。
英文摘要
Can programmable radio propagation serve as computational depth rather than only as a communication channel or one-shot analog transform? We introduce the Radio Alternating Operator Ansatz (RAOA), a recurrent computing architecture that alternates an energy-derived problem update with a mixing update over a persistent latent state. Recomputing the problem field after each mix makes repeated passes compositional even when the same learned controls are reused across depth. We evaluate this idea through exact discrete optimization, constrained programmable-propagation simulation, and pretrained-model adaptation. On discrete objectives, repeated execution can improve solution quality without increasing the learned-control count, and the same formulation handles higher-order interactions directly. A passive phase-only free-space model further shows that the required operators can be approximated by programmable propagation while retaining useful downstream behavior despite realization error. When inserted as a zero-initialized residual adapter, RAOA adapts pretrained language models with WikiText performance close to a matched shallow MLP across three model families, while reasoning-task transfer remains model-dependent. Together, these results connect alternating-operator computation, programmable radio propagation, and neural adaptation within one recurrent framework. The RF realization evidence is simulation-based rather than a hardware demonstration.
Comments31 pages, 6 figures
