Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors
This addresses the need for reliable uncertainty quantification in deep learning for critical applications, representing a novel method for a known bottleneck.
The paper tackles the challenge of producing well-calibrated and sharp prediction intervals for deep learning models in critical applications, achieving significant improvements in model fidelity and calibration error over existing methods.
With rapid adoption of deep learning in critical applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent uncertainties. While identifying all sources that account for the stochasticity of models is challenging, it is common to augment predictions with confidence intervals to convey the expected variations in a model's behavior. We require prediction intervals to be well-calibrated, reflect the true uncertainties, and to be sharp. However, existing techniques for obtaining prediction intervals are known to produce unsatisfactory results in at least one of these criteria. To address this challenge, we develop a novel approach for building calibrated estimators. More specifically, we use separate models for prediction and interval estimation, and pose a bi-level optimization problem that allows the former to leverage estimates from the latter through an \textit{uncertainty matching} strategy. Using experiments in regression, time-series forecasting, and object localization, we show that our approach achieves significant improvements over existing uncertainty quantification methods, both in terms of model fidelity and calibration error.