在量子纯态流形上构建相位对齐的确定性生成模型,解决传统方法的几何错配问题。
Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned Transport
- 基于复射影空间设计相位对齐的确定性传输路径,学习切向速度场。
- 在高维、多模态及相干敏感任务中显著优于传统欧氏流模型。
- 适用于量子机器学习、量子态生成等需要高保真度的任务。
量子纯态系综位于复射影空间上,使得传统的平坦欧氏生成建模在几何上不匹配。我们提出内在流匹配(IFM),一种在 $\b{CP}^{d-1}$ 上的确定性传输框架,通过潘查拉特南相位对齐的条件路径学习切向速度场。IFM 用流形概率流替代局部梯度教师与反向随机采样,并通过水平参数化消除了冗余的环境方向。我们证明了 IFM 目标可恢复诱导边缘传输场,表示确定性的投影系综流,并提供端点与稳定性保证。实验表明,IFM 在更高比特数、多模态、自旋相干、物理启发以及振幅编码的 MNIST 图像向量基准测试中,通常优于环境欧氏流匹配,尤其在高维与相干敏感任务中表现最优,但并非在所有指标上均一致提升。
原文摘要 · Abstract (English)
Quantum pure-state ensembles live on complex projective space, making flat Euclidean generative modeling geometrically mismatched. We introduce Intrinsic Flow Matching (IFM), a deterministic transport framework on $\mathbb{CP}^{d-1}$ that learns tangent velocity fields using Pancharatnam phase-aligned conditional paths. IFM replaces local score teachers and reverse-time stochastic sampling with manifold probability flow, while horizontal parameterization removes redundant ambient directions. We show that the IFM objective recovers the induced marginal transport field, represents deterministic projective ensemble flows, and yields endpoint and stability guarantees. Empirically, IFM often improves over ambient Euclidean flow matching across higher-qubit, multimodal, spin-coherent, physics-inspired, and amplitude-encoded MNIST image-vector benchmarks, with strongest gains on high-dimensional and coherence-sensitive tasks but not uniformly across every metric.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。