Traditional neural networks are simple to train but they produce overconfident predictions, while Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming. This paper introduces a new approach, direct uncertainty quantification (DirectUQ), that combines their advantages where the neural network directly models uncertainty in output space, and captures both aleatoric and epistemic uncertainty. DirectUQ can be derived as an alternative variational lower bound, and hence benefits from collapsed variational inference that provides improved regularizers. On the other hand, like non-probabilistic models, DirectUQ enjoys simple training and one can use Rademacher complexity to provide risk bounds for the model. Experiments show that DirectUQ and ensembles of DirectUQ provide a good tradeoff in terms of run time and uncertainty quantification, especially for out of distribution data.

翻译：传统神经网络简单易修,但能产生过于自信的预测,而贝耶斯神经网络则提供良好的不确定性量化,但最优化是耗时的。本文引入了一种新的方法,即直接不确定性量化(DirectUQ),将神经网络直接模拟产出空间不确定性的优势结合起来,同时捕捉了空气中的不确定性和感知不确定性。直接UQ可以作为一种替代变异性较低约束而产生,从而从崩溃的变异性推断中获益,从而提供更好的规范化者。另一方面,像非概率模型一样,直接UQ接受简单培训,可以使用Rademacher复杂度为模型提供风险界限。实验显示,直接UQ和直接UQ的集合在运行时间和不确定性量化方面提供了良好的权衡,特别是对于分配数据之外的情况。