- Abstract: In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling com- ponents of the future state which are predictable from those which are inherently unpredictable, and encoding the unpredictable components into a low-dimensional latent variable which is fed into the forward model. Our method uses a simple su- pervised training objective which is fast and easy to train. We evaluate it in the context of video prediction on multiple datasets and show that it is able to consi- tently generate diverse predictions without the need for alternating minimization over a latent space or adversarial training.
- TL;DR: A simple and easy to train method for multimodal prediction in time series.