Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
This work addresses the challenge of scaling multivariate forecasting to high dimensions while capturing dependencies, which is incremental as it combines existing autoregressive models with normalizing flows.
The authors tackled the problem of multivariate time series forecasting by developing an autoregressive deep learning model that uses conditioned normalizing flows to model statistical dependencies, improving accuracy over state-of-the-art methods on real-world datasets with thousands of interacting time-series.
Time series forecasting is often fundamental to scientific and engineering problems and enables decision making. With ever increasing data set sizes, a trivial solution to scale up predictions is to assume independence between interacting time series. However, modeling statistical dependencies can improve accuracy and enable analysis of interaction effects. Deep learning methods are well suited for this problem, but multivariate models often assume a simple parametric distribution and do not scale to high dimensions. In this work we model the multivariate temporal dynamics of time series via an autoregressive deep learning model, where the data distribution is represented by a conditioned normalizing flow. This combination retains the power of autoregressive models, such as good performance in extrapolation into the future, with the flexibility of flows as a general purpose high-dimensional distribution model, while remaining computationally tractable. We show that it improves over the state-of-the-art for standard metrics on many real-world data sets with several thousand interacting time-series.