随机薛定谔扩散模型用于纯态集合生成
Local-Time Riemannian Score Matching on the Quantum Pure-State Manifold
AI总结:
本文提出随机薛定谔扩散模型(SSDMs),在复射影空间CP^{d-1}上构建基于分数的生成框架,通过局部欧几里得奥本海姆-乌尔申贝格近似实现无解析过渡密度的训练,提升量子机器学习的泛化能力。
摘要:
在量子机器学习(QML)中,经典数据通常被编码为量子纯态并直接处理为量子表示,推动了在底层表示层面生成模型的发展,该模型从底层纯态集合中采样新量子态,而非从扰动的经典输入重新准备。然而,将具有明确反向时间采样器的分数扩散模型扩展到量子纯态集合仍具挑战性,由于复射影空间CP^{d-1}的非欧几里得几何和过渡密度的不可行性。我们提出了随机薛定谔扩散模型(SSDMs),一种内在的基于分数的生成框架,配备了Fubini-Study(FS)度量。SSDMs通过随机薛定谔方程(SSE)实现正向黎曼扩散,并推导出由黎曼分数∇_{FS} log p_t驱动的反向时间动力学。为了在没有解析过渡密度的情况下进行训练,我们引入了一个基于FS正常坐标中局部欧几里得奥本海姆-乌尔申贝格近似的局部时间目标,从而得到一个映射回流形的解析教师分数。实验表明,SSDMs能够忠实捕捉目标纯态集合的统计特性,包括可观测量的矩、重叠核MMD和纠缠度量,并且SSDM生成的量子表示通过表示层面的数据增强提升了下游QML的泛化能力。
英文摘要:
Score-based diffusion can be defined intrinsically on the manifold of quantum pure states, $\mathbb{CP}^{d-1}$ with the Fubini--Study metric, but no closed-form transition density is available, so the score must be supervised by a local-time teacher taken from the Euclidean limit of the diffusion in normal coordinates. This paper is about what makes that teacher work, and where it stops working. Three training choices turn out not to be incidental: the increment must be divided by the diffusion clock rather than by the elapsed time, since the published expression assumes unit diffusion and a non-unit schedule introduces a time-change mismatch varying by a factor of $400$ across the horizon; the logarithm and exponential maps should be the closed-form Fubini--Study ones, which is the largest single effect we measure; and the global phase must be randomised, because horizontal projection alone does not make a score network descend to the quotient. With these choices the model improves on the published Riemannian local-time baseline in every cell of an eight-benchmark, four-metric comparison over ten seeds, significantly on five of eight after Holm correction, and beats an ambient Euclidean baseline by an order of magnitude everywhere. We then bound what the approximation costs by replacing it with the exact heat kernel of $\mathbb{CP}^{d-1}$, computable up to complex dimension seven, where the local-time teacher loses a factor of $1.2$ to $2.7$.
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。