Time series with non-uniform intervals occur in many applications, and are difficulttomodel usingstandard recurrent neural networks(RNNs).

We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE).

In this paper, we intent to handle this emerging issue.

Learning to detect and encode temporal regularities (TRs) in events is a prerequisite for human-like intelligence. These regularities should be formed from limited event samples and stored as easily retrievable representations.

The work was conducted during the internship of Y uqi Chen and Y uchen Fang at Microsoft Research.

Interacting systems are prevalent in nature.

This factorization enables closed-form updates during optimization (see below).