Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling
This work addresses uncertainty modeling for machine learning practitioners, offering a method that balances flexibility and reliability, though it is incremental as it builds on existing Normalizing Flow techniques.
The paper tackled the problem of estimating both epistemic and aleatoric uncertainty in machine learning by proposing an ensemble of Normalizing Flows with fixed dropout masks, which achieved accurate uncertainty estimates in experiments like 1D sinusoidal data and Hopper.
In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are state-of-the-art in modeling aleatoric uncertainty. The ensembles are created via sets of fixed dropout masks, making them less expensive than creating separate NF models. We demonstrate how to leverage the unique structure of NFs, base distributions, to estimate aleatoric uncertainty without relying on samples, provide a comprehensive set of baselines, and derive unbiased estimates for differential entropy. The methods were applied to a variety of experiments, commonly used to benchmark aleatoric and epistemic uncertainty estimation: 1D sinusoidal data, 2D windy grid-world ($\it{Wet Chicken}$), $\it{Pendulum}$, and $\it{Hopper}$. In these experiments, we setup an active learning framework and evaluate each model's capability at measuring aleatoric and epistemic uncertainty. The results show the advantages of using NF ensembles in capturing complicated aleatoric while maintaining accurate epistemic uncertainty estimates.