arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.08237cs.LGcs.AIstat.ML
收藏

从聚合数据中学习深度隐藏的非线性动力学

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data

Georgia Tech(佐治亚理工学院);Tsinghua University(清华大学);Ant Financial Services Group(蚂蚁金融服务集团);University of Melbourne(墨尔本大学)

Yisen Wang, Bo Dai, Lingkai Kong, Sarah Monazam Erfani, James Bailey, Hongyuan Zha

摘要:

从扩散数据中学习非线性动力学是一个具有挑战性的问题,因为观察到的个体在不同的时间点可能不同,通常遵循聚集行为。现有的工作不能很好地处理这些任务,因为他们的动态模型,无论是直接观察或强制执行完整的纵向个人水平的轨迹的可用性。然而,在大多数实际应用中,这些要求是不现实的:演化动力学可能太复杂而无法直接根据观测结果建模,并且由于技术限制、实验成本和/或隐私问题,可能无法获得个体水平的轨迹。为了解决这些挑战,我们制定了一个模型的扩散动力学的{ \em隐藏的随机过程}通过引入隐藏变量的灵活性,并学习隐藏的动态直接对{ \em聚合观测},而不需要任何个人级别的轨迹。本文提出了一个具有Wasserstein距离的动态生成模型LEGEND,并证明了它的理论保证。在一系列合成和真实世界数据集上的实验表明,与最先进的基线相比,LEGEND具有非常强大的性能。

英文摘要:

Learning nonlinear dynamics from diffusion data is a challenging problem since the individuals observed may be different at different time points, generally following an aggregate behaviour. Existing work cannot handle the tasks well since they model such dynamics either directly on observations or enforce the availability of complete longitudinal individual-level trajectories. However, in most of the practical applications, these requirements are unrealistic: the evolving dynamics may be too complex to be modeled directly on observations, and individual-level trajectories may not be available due to technical limitations, experimental costs and/or privacy issues. To address these challenges, we formulate a model of diffusion dynamics as the {\em hidden stochastic process} via the introduction of hidden variables for flexibility, and learn the hidden dynamics directly on {\em aggregate observations} without any requirement for individual-level trajectories. We propose a dynamic generative model with Wasserstein distance for LEarninG dEep hidden Nonlinear Dynamics (LEGEND) and prove its theoretical guarantees as well. Experiments on a range of synthetic and real-world datasets illustrate that LEGEND has very strong performance compared to state-of-the-art baselines.

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。

↑