Learning accurate predictive models of real-world dynamic phenomena (e.g., climate, biological) remains a challenging task. One key issue is that the data generated by both natural and artificial processes often comprise time series that are irregularly sampled and/or contain missing observations. In this work, we propose the Neural Continuous-Discrete State Space Model (NCDSSM) for continuous-time modeling of time series through discrete-time observations. NCDSSM employs auxiliary variables to disentangle recognition from dynamics, thus requiring amortized inference only for the auxiliary variables. Leveraging techniques from continuous-discrete filtering theory, we demonstrate how to perform accurate Bayesian inference for the dynamic states. We propose three flexible parameterizations of the latent dynamics and an efficient training objective that marginalizes the dynamic states during inference. Empirical results on multiple benchmark datasets across various domains show improved imputation and forecasting performance of NCDSSM over existing models.

提出了神经连续-离散状态空间模型(NCDSSM)，用于对时间序列进行连续时间建模。该模型使用辅助变量进行识别和动态分离，从而仅需要为辅助变量进行摊销推理。通过连续离散滤波理论，提出了三种灵活的潜在动态参数化方法和一种能够较快地进行后验推理的训练目标函数。实验结果表明，NCDSSM在多个基准数据集上都比现有模型具有更好的插补和预测性能。

神经连续-离散状态空间模型用于不规则采样的时间序列