arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.03534math.NAcs.NAstat.ML
收藏

神经主动流形:用于不确定性量化的非线性降维

Neural active manifolds: nonlinear dimensionality reduction for uncertainty quantification

Scuola Normale Superiore(高等师范学校);Stanford University(斯坦福大学);Sandia National Laboratories(桑迪亚国家实验室);University of Notre Dame(圣母大学)

Andrea Zanoni, Gianluca Geraci, Matteo Salvador, Alison L. Marsden, Daniele E. Schiavazzi

AI总结:

本研究提出一种基于自编码器的神经主动流形(NeurAM)非线性降维方法,无需梯度即可捕捉高成本模型输出变异性,可辅助科学计算多查询任务,经理论和数值验证能降低多保真度采样估计方差,性能优于现有方法。

摘要:

我们提出了一种专为计算成本高昂的数学模型设计的非线性降维新方法。我们利用自编码器发现一维神经主动流形(NeurAM),该流形通过同时学习的、输入位于该流形上的代理模型,捕捉模型输出的变异性。我们的方法仅依赖模型评估,不需要梯度信息。所提出的降维框架可用于辅助科学计算中的外循环多查询任务,例如灵敏度分析和多保真度不确定性传播。具体而言,我们通过理想条件下的理论证明和挑战性测试用例的数值验证,展示了如何利用NeurAM,通过在发现的模型间共享的低维流形上对模型进行采样,获得方差降低的多保真度采样估计量。多个数值示例阐明了所提出的降维策略的主要特征,并凸显了其相较于文献中现有方法的优势。

英文摘要:

We present a new approach for nonlinear dimensionality reduction, specifically designed for computationally expensive mathematical models. We leverage autoencoders to discover a one-dimensional neural active manifold (NeurAM) capturing the model output variability, through the aid of a simultaneously learnt surrogate model with inputs on this manifold. Our method only relies on model evaluations and does not require the knowledge of gradients. The proposed dimensionality reduction framework can then be applied to assist outer loop many-query tasks in scientific computing, like sensitivity analysis and multifidelity uncertainty propagation. In particular, we prove, both theoretically under idealized conditions, and numerically in challenging test cases, how NeurAM can be used to obtain multifidelity sampling estimators with reduced variance by sampling the models on the discovered low-dimensional and shared manifold among models. Several numerical examples illustrate the main features of the proposed dimensionality reduction strategy and highlight its advantages with respect to existing approaches in the literature.

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。

↑