arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2611.06711cs.LGphysics.comp-ph
收藏

能量引导传输:无投影的物理信息流匹配

Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching

Sapienza University of Rome(罗马第一大学)

Giuliano Galadini, Aurelio Uncini, Danilo Comminiello

AI总结:

该研究提出能量引导传输框架,将物理约束转化为平滑势能,通过连续耗散力引导生成状态贴合物理流形,在保持流动力学的同时提升生成稳定性与推理效率。

摘要:

深度生成模型,尤其是流匹配(Flow Matching)框架,已成为合成复杂物理系统的强大工具。然而,标准架构仍完全由统计驱动,对底层控制方程一无所知,在推理过程中常违反基本物理约束。现有用于强制执行这些约束的零样本方法通常依赖刚性代数投影,虽对稀疏边界条件有效,但将此类离散几何校正应用于密集的全域偏微分方程(PDE)可能会破坏概率路径,使其偏离学习到的流形并引入大量计算开销。为解决这些挑战,我们提出能量引导传输(Energy-Guided Transport),这是一种新颖的无训练框架,将非线性物理约束表述为平滑势能景观。我们的方法不中断常微分方程(ODE)积分,而是直接对中间生成状态施加连续耗散力,引导其向物理流形靠近。通过反向自动微分隐式计算该力,我们的框架在保持流自然动力学的同时,维持了高效的O(N)算法复杂度。我们在各种一维和二维物理系统(包括混沌纳维-斯托克斯方程)上对框架进行了广泛评估。我们的方法实现了无结构发散的稳定生成,与最先进方法相比显著改善了稳定性-精度权衡,且相较于精确投影策略大幅加速了推理。代码可在以下URL获取:this https URL。

英文摘要:

Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems. However, standard architectures remain purely statistically driven and agnostic to the underlying governing equations, often violating fundamental physical constraints during inference. Existing zero-shot approaches designed to enforce these constraints typically rely on rigid algebraic projections. While effective for sparse boundary conditions, applying such discrete geometric corrections to dense, full-domain PDEs may disrupt the probability path, \rev{potentially deviating from the learned manifold and introducing substantial computational overhead}. To address these challenges, we introduce Energy-Guided Transport, a novel training-free framework that formulates non-linear physical constraints as a smooth potential energy landscape. Rather than interrupting the ODE integration, our method applies a continuous dissipative force directly to the intermediate generative states, steering them toward the physical manifold. By evaluating this force implicitly via reverse-mode automatic differentiation, our framework preserves the natural dynamics of the flow while maintaining an efficient $\mathcal{O}(N)$ algorithmic complexity. We extensively evaluate our framework across various 1D and 2D physical systems, including the chaotic Navier-Stokes equations. Our method achieves stable generation without structural divergence, significantly improves the stability-accuracy trade-off compared to state-of-the-art methods, and substantially accelerates inference with respect to exact projection strategies. Code available at: https://github.com/ispamm/Projection-free-energy-guided-flow-matching.

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。

↑