Autoregressive Quantile Flows for Predictive Uncertainty Estimation

Understand

Numerous applications of machine learning involve representing probability distributions over high-dimensional data.

• We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a novel objective based on proper scoring rules.
• Our objective does not require calculating computationally expensive determinants of Jacobians during training and supports new types of neural architectures, such as neural autoregressive flows from which it is easy to sample.
• We leverage these models in quantile flow regression, an approach that parameterizes predictive conditional distributions with flows, resulting in improved probabilistic predictions on tasks such as time series forecasting and object detection.