arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.00161cs.LGcs.AI
收藏

DiffHybrid-UQ:面向可微混合神经建模的不确定性量化

DiffHybrid-UQ: Uncertainty Quantification for Differentiable Hybrid Neural Modeling

University of Notre Dame(圣母大学)

Deepak Akhare, Tengfei Luo, Jian-Xun Wang

AI总结:

本文提出DiffHybrid-UQ方法,结合深度集成贝叶斯学习与非线性变换,有效量化混合神经可微模型中的偶然与认知不确定性,适用于并行计算且在常微分和偏微分方程问题中验证了其优越性。

摘要:

混合神经可微模型标志着科学机器学习领域的重大进展。这些模型将已知物理的数值表示整合到深度神经网络中,提供了增强的预测能力,并展现出在复杂物理系统数据驱动建模方面的巨大潜力。然而,一个关键且尚未解决的挑战在于量化源自多个来源的固有不确定性。为填补这一空白,我们引入了一种新方法 DiffHybrid-UQ,利用深度集成贝叶斯学习和非线性变换的优势,在混合神经可微模型中实现高效且有效的不确定性传播与估计。具体而言,我们的方法能有效识别并量化两类不确定性:由数据噪声引起的偶然不确定性,以及由模型形式差异和数据稀疏性导致的认知不确定性。这通过贝叶斯模型平均框架实现,其中偶然不确定性通过混合神经模型进行建模。无迹变换在使这些不确定性流经混合模型内的非线性函数方面发挥了关键作用。相比之下,认知不确定性则通过随机梯度下降(SGD)轨迹的集成进行估计。该方法为网络参数和物理参数的后验分布提供了实用的近似。值得注意的是,DiffHybrid-UQ 框架设计简洁且具有高可扩展性,使其适用于并行计算环境。所提方法的优越性已通过常微分方程和偏微分方程控制的问题得到验证。

英文摘要:

The hybrid neural differentiable models mark a significant advancement in the field of scientific machine learning. These models, integrating numerical representations of known physics into deep neural networks, offer enhanced predictive capabilities and show great potential for data-driven modeling of complex physical systems. However, a critical and yet unaddressed challenge lies in the quantification of inherent uncertainties stemming from multiple sources. Addressing this gap, we introduce a novel method, DiffHybrid-UQ, for effective and efficient uncertainty propagation and estimation in hybrid neural differentiable models, leveraging the strengths of deep ensemble Bayesian learning and nonlinear transformations. Specifically, our approach effectively discerns and quantifies both aleatoric uncertainties, arising from data noise, and epistemic uncertainties, resulting from model-form discrepancies and data sparsity. This is achieved within a Bayesian model averaging framework, where aleatoric uncertainties are modeled through hybrid neural models. The unscented transformation plays a pivotal role in enabling the flow of these uncertainties through the nonlinear functions within the hybrid model. In contrast, epistemic uncertainties are estimated using an ensemble of stochastic gradient descent (SGD) trajectories. This approach offers a practical approximation to the posterior distribution of both the network parameters and the physical parameters. Notably, the DiffHybrid-UQ framework is designed for simplicity in implementation and high scalability, making it suitable for parallel computing environments. The merits of the proposed method have been demonstrated through problems governed by both ordinary and partial differentiable equations.

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。

↑