We propose a novel probabilistic framework for modeling stochastic dynamics with the
rigorous use of stochastic optimal control theory. The proposed model called the neural …

Learning accurate predictive models of real-world dynamic phenomena (eg, climate,
biological) remains a challenging task. One key issue is that the data generated by both …

Sensing signals of many real-world network systems, such as traffic network or microgrid,
could be sparse and irregular in both spatial and temporal domains due to reasons such as …

Monitoring data of real-world networked systems could be sparse and irregular due to node
failures or packet loss, which makes it a challenge to model the continuous dynamics of …

Stochastic modeling for time series data often arises in many real-world applications.
Although linear methods have been well-studied for low-dimensional sequential data, these …