利用正交光子空间 Ising 机求解 20736 节点加权 Max-Cut 问题
20736-node Weighted Max-Cut Problem Solving by Quadrature Photonic Spatial Ising Machine
AI总结：
提出单 SLM 的正交光子空间-Euler Ising 机及噪声增强方法，实现灵活大规模自旋配置与翻转，实验求解 20736 节点 Max-cut 并优于数字仿真和启发式算法。
摘要：
为应对具有挑战性的组合优化问题，基于受自然启发的 Ising 模型的模拟计算机正吸引越来越多关注，以期颠覆性克服传统电子计算机即将面临的限制。光子空间 Ising 机已成为一种独特而原始的解决方案，具备全连接能力，可用于求解大规模 Max-cut 问题。然而，自旋配置和翻转需要两组独立的空间光调制器（SLM）分别进行振幅和相位调制，这将给光学校准与耦合带来巨大的工程难度。我们报道一种新型正交光子空间-Euler Ising 机，可在单个空间光调制器中实现大规模、灵活的自旋相互作用配置与自旋翻转，并开发了一种通过向检测到的光信号中加入数字白噪声来实现噪声增强的方法。我们通过实验表明，该方案加速求解了（非）加权、（非）全连接的 20736 节点 Max-cut 问题，相较于数字计算机上的仿真和启发式算法结果具有明显优势。
英文摘要：
To tackle challenging combinatorial optimization problems, analog computing machines based on the nature-inspired Ising model are attracting increasing attentions in order to disruptively overcome the impending limitations on conventional electronic computers. Photonic spatial Ising machine has become an unique and primitive solution with all-to-all connections to solve large-scale Max-cut problems. However, spin configuration and flipping requires two independent sets of spatial light modulators (SLMs) for amplitude and phase modulation, which will lead to tremendous engineering difficulty of optical alignment and coupling. We report a novel quadrature photonic spatial-Euler Ising machine to realize large-scale and flexible spin-interaction configuration and spin-flip in a single spatial light modulator, and develop a noise enhancement approach by adding digital white noise onto detected optical signals. We experimentally show that such proposal accelerates solving (un)weighted, (non)fully connected, 20736-node Max-cut problems, which offers obvious advantages over simulation and heuristic algorithm results in digital computers.
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。
