Trustworthy ML systems should not only return accurate predictions, but also
a reliable representation of their uncertainty. Bayesian methods are commonly
used to quantify both aleatoric and epistemic uncertainty, but alternative
approaches, such as evidential deep learning methods, have become popular in
recent years. The latter group of methods in essence extends empirical risk
minimization (ERM) for predicting second-order probability distributions over
outcomes, from which measures of epistemic (and aleatoric) uncertainty can be
extracted. This paper presents novel theoretical insights of evidential deep
learning, highlighting the difficulties in optimizing second-order loss
functions and interpreting the resulting epistemic uncertainty measures. With a
systematic setup that covers a wide range of approaches for classification,
regression and counts, it provides novel insights into issues of
identifiability and convergence in second-order loss minimization, and the
relative (rather than absolute) nature of epistemic uncertainty measures.

可信的机器学习系统不仅应返回准确的预测结果，还应提供可靠的不确定性表示。贝叶斯方法通常用于量化生成论和认知性不确定性，但近年来，备选方法，如证据深度学习方法，已变得流行。这篇论文提出了证据深度学习的新理论洞见，强调了优化二阶损失函数和解释由此得出的认知性不确定度度量的困难。通过一个系统的实验设置，涵盖了分类，回归和计数的多种方法，对二阶损失最小化中的确认性和收敛性问题，以及认知不确定性度量的相对（而不是绝对）性质提供了新的见解。