双保真采样超网络框架用于材料响应建模与不确定性量化
Applied bifidelity material response model construction and uncertainty quantification with a sampling hypernetwork
这篇 arXiv 论文面向做仿真替代模型或工程不确定性量化的人。它把双保真建模和 Langevin 采样超网络结合起来，在实验、仿真和合成数据上验证，比单点拟合能给出后验不确定性，实验数据不够时也能用低保真数据补。
arXiv 论文 2611.10429 提出一种双保真 Langevin 采样超网络框架，在高保真数据稀缺、低保真数据相对充足的场景下构建概率神经响应模型。
该方法学习模型参数的后验分布而非单一确定性拟合，通过共享潜变量表示连接低、高保真响应，实现保真度之间的参数共享与迁移学习。论文引入多项方法学改进：稳定性增强的漂移模型、分阶段与条件化训练策略、Langevin 轨迹的自适应初始化，以及更好利用保真度间相关性的训练流程。
这些改进提升了收敛表现，减少了获得代表性后验集合所需的采样量，并在数据受限条件下给出更可靠的预测不确定性。方法在实验数据、高保真仿真数据和合成数据上完成验证，为构建不确定性感知的代理模型提供了更稳定的工作流，同时借助学习到的后验结构保持可解释性。
Applied bifidelity material response model construction and uncertainty quantification with a sampling hypernetwork
Multifidelity modeling offers a practical route to accurate prediction and uncertainty quantification when high-fidelity data are scarce but lower-fidelity data are comparatively abundant. This work develops a bifidelity Langevin sampling hypernetwork framework that constructs probabilistic neu- ral response models by learning a posterior distribution over model parameters rather than a single deterministic fit. The method combines a flexible shared-latent data representation for low- and high-fidelity responses, enabling parameter sharing and transfer learning between the fidelities. We introduce several methodological enhancements to improve the robustness and efficiency of this ap- proach, including stability-promoting drift models, staged and conditional training strategies, adap- tive initialization of Langevin trajectories, and training procedures designed to better exploit corre- lations between fidelity levels. These additions improve convergence behavior, reduce the sampling effort required to obtain representative posterior ensembles, and provide more reliable predictive uncertainty in data-limited regimes. The resulting framework makes more effective use of available multifidelity data while preserving interpretability through the learned posterior structure, yielding improved predictive performance, better uncertainty characterization, and a more stable workflow for constructing uncertainty-aware surrogate models. The method is demonstrated on experimental, high-fidelity simulation and illustrative synthetic data.
本条情报归属 AITOP「论文」核心追踪栏目。涉及核心实体与技术议题包括：不确定性量化、Langevin采样、超网络、多保真建模，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Reese E. Jones, Cosmin Safta, Dan Bolintineau, Craig M. Hamel, Gianluca Geraci, Sharlotte LB Kramer），经 AITOP 多维评分管线结构化提炼。