标题： 神经网络中的不确定性：近似贝叶斯集成 显示英文标题

标题： Uncertainty in Neural Networks: Approximately Bayesian Ensembling

摘要： 理解神经网络（NN）预测的不确定性对于许多目的都是至关重要的。贝叶斯框架为此提供了一种合理的方法，然而由于参数和数据数量庞大，将其应用于NNs具有挑战性。集成NNs提供了一种易于实现且可扩展的不确定性量化方法，然而它一直受到批评，因为它不是贝叶斯的。这项工作提出对通常过程的一个修改，我们认为这确实会导致近似贝叶斯推理；对从可以设置为先验分布中抽取的值进行参数正则化。在简化设置中的理论分析表明，恢复的后验分布中心是正确的，但倾向于低估边缘方差并高估相关性。然而，两个条件可能导致精确恢复。我们认为这些条件在NNs中部分存在。实证评估表明它比标准集成有优势，并且与变分方法相当。 显示英文摘要

摘要： Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters and data. Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian. This work proposes one modification to the usual process that we argue does result in approximate Bayesian inference; regularising parameters about values drawn from a distribution which can be set equal to the prior. A theoretical analysis of the procedure in a simplified setting suggests the recovered posterior is centred correctly but tends to have an underestimated marginal variance, and overestimated correlation. However, two conditions can lead to exact recovery. We argue that these conditions are partially present in NNs. Empirical evaluations demonstrate it has an advantage over standard ensembling, and is competitive with variational methods.