Retrospective Uncertainties for Deep Models using Vine Copulas
This addresses uncertainty estimation for deep learning practitioners, offering a flexible solution without architectural changes, though it is incremental as it builds on existing copula methods.
The paper tackled the challenge of uncertainty estimation in deep models by proposing a vine copula-based approach that supplements any network retrospectively, achieving reliable and better-calibrated uncertainty estimates comparable to state-of-the-art built-in solutions.
Despite the major progress of deep models as learning machines, uncertainty estimation remains a major challenge. Existing solutions rely on modified loss functions or architectural changes. We propose to compensate for the lack of built-in uncertainty estimates by supplementing any network, retrospectively, with a subsequent vine copula model, in an overall compound we call Vine-Copula Neural Network (VCNN). Through synthetic and real-data experiments, we show that VCNNs could be task (regression/classification) and architecture (recurrent, fully connected) agnostic while providing reliable and better-calibrated uncertainty estimates, comparable to state-of-the-art built-in uncertainty solutions.