arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10451cs.LGphysics.comp-ph
收藏

具有分布级物理先验的多模态条件混合模型

A Multimodal Conditional Mixture Model with Distribution-Level Physics Priors

Jinkyo Han, Bahador Bahmani

AI总结:

本文提出了一种基于混合密度表示的物理信息多模态条件建模框架,通过组件特定的正则化项嵌入物理知识,以更简单和可解释的方式处理多模态性问题。

摘要:

许多科学和工程系统表现出本质上多模态的行为,这种行为源于潜在的模式切换和非唯一的物理机制。在这种情况下,以物理一致和可解释的方式学习可接受结果的完整条件分布仍是一个挑战。尽管最近的机器学习进展使强大的多模态生成建模成为可能,但将其与受物理约束的科学建模结合仍非 trivial,尤其是在必须保持物理结构或数据有限时。本文开发了一种基于混合密度表示的物理信息多模态条件建模框架。混合密度网络(MDNs)提供了一种显式且可解释的多模态条件分布参数化。通过组件特定的正则化项将物理知识嵌入其中,这些正则化项惩罚违反控制方程或物理定律的违反。这种形式自然地容纳非唯一性和随机性,同时保持计算效率且易于对上下文输入进行条件。所提出的框架在一系列科学问题上进行了评估,这些问题中多模态性源于内在的物理机制而非观测噪声,包括非线性动力系统中的分岔现象、随机偏微分方程和原子尺度冲击动力学。此外,所提出的方法与条件流匹配(CFM)模型进行了比较,后者是代表性的最先进生成建模方法,证明MDNs可以在保持简单且更可解释的公式的同时实现竞争性的性能。

英文摘要:

Many scientific and engineering systems exhibit intrinsically multimodal behavior arising from latent regime switching and non-unique physical mechanisms. In such settings, learning the full conditional distribution of admissible outcomes in a physically consistent and interpretable manner remains a challenge. While recent advances in machine learning have enabled powerful multimodal generative modeling, their integration with physics-constrained scientific modeling remains nontrivial, particularly when physical structure must be preserved or data are limited. This work develops a physics-informed multimodal conditional modeling framework based on mixture density representations. Mixture density networks (MDNs) provide an explicit and interpretable parameterization of multimodal conditional distributions. Physical knowledge is embedded through component-specific regularization terms that penalize violations of governing equations or physical laws. This formulation naturally accommodates non-uniqueness and stochasticity while remaining computationally efficient and amenable to conditioning on contextual inputs. The proposed framework is evaluated across a range of scientific problems in which multimodality arises from intrinsic physical mechanisms rather than observational noise, including bifurcation phenomena in nonlinear dynamical systems, stochastic partial differential equations, and atomistic-scale shock dynamics. In addition, the proposed method is compared with a conditional flow matching (CFM) model, a representative state-of-the-art generative modeling approach, demonstrating that MDNs can achieve competitive performance while offering a simpler and more interpretable formulation.

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。

↑