SDEs are then decoded into an observable space with complex structure.

We base the justification on the following two propositions. Work developed during an internship at Borealis AI. Poisson processes for training and test. For the mixture of OU processes (MOU), we sample 5000 sequences from each of two different OU processes and mix them to obtain 10000 sequences. As mentioned in Section 5.2 of the paper, we compare our models against the baselines on three datasets: Mujoco-Hopper, Beijing Air-Quality dataset (BAQD), and PTB Diagnostic The sequence length of the Mujoco-Hopper dataset is 200 and the sequence length of BAQD is 168.

In this work, we propose a novel type of normalizing flow driven by a differential deformation of the Wiener process.

We would like to thank all the reviewers for their thoughtful comments. We will respond to each reviewer's questions Itô diffusion processes with tractable finite-dimensional distributions (FDD). To show the correctness of Eqs. Since our experiments focus on low-dimensional data, the time cost is not a major bottleneck. We agree with the reviewer's comment on Eq.(12):