arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.10616cs.LGphysics.soc-phq-bio.PE
收藏

学习动力系统的物理建模与数据驱动建模的桥梁

Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems

UC San Diego(加州大学圣迭戈分校);Amazon Research(亚马逊研究院);Amazon(亚马逊);Carnegie Mellon University(卡内基梅隆大学)

Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu

摘要:

当一些变量无法观测时,我们如何学习一个动力系统来进行预测?例如,在COVID-19中,我们希望预测感染和死亡病例的数量,但我们不知道易感和暴露人群的数量。虽然力学房室模型广泛用于流行病建模,但数据驱动模型正在出现用于疾病预测。我们首先将基于物理的模型的学习形式化为AutoODE,它利用自动微分来估计模型参数。通过对COVID-19预测的基准研究,我们注意到基于物理的机械模型显著优于深度学习。与最好的深度学习竞争对手相比,我们的方法提前7天预测COVID-19的平均绝对误差减少了57.4%。这种性能差异凸显了由于分布偏移而导致的动态系统学习中的泛化问题。我们确定了两种情况下,分布偏移可能发生:数据域的变化和参数域的变化(系统动力学)。通过对几个动力系统的系统实验,我们发现深度学习模型在这两种情况下都无法很好地预测。虽然很多关于分布偏移的研究都集中在数据域的变化上,但我们的工作呼吁人们重新思考学习动力系统的泛化。

英文摘要:

How can we learn a dynamical system to make forecasts, when some variables are unobserved? For instance, in COVID-19, we want to forecast the number of infected and death cases but we do not know the count of susceptible and exposed people. While mechanics compartment models are widely used in epidemic modeling, data-driven models are emerging for disease forecasting. We first formalize the learning of physics-based models as AutoODE, which leverages automatic differentiation to estimate the model parameters. Through a benchmark study on COVID-19 forecasting, we notice that physics-based mechanistic models significantly outperform deep learning. Our method obtains a 57.4% reduction in mean absolute errors for 7-day ahead COVID-19 forecasting compared with the best deep learning competitor. Such performance differences highlight the generalization problem in dynamical system learning due to distribution shift. We identify two scenarios where distribution shift can occur: changes in data domain and changes in parameter domain (system dynamics). Through systematic experiments on several dynamical systems, we found that deep learning models fail to forecast well under both scenarios. While much research on distribution shift has focused on changes in the data domain, our work calls attention to rethink generalization for learning dynamical systems.

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。

↑