It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task consists of learning a diversity of predictors that all can explain the training data. This information can be used to estimate the epistemic uncertainty at a given newly observed instance in terms of a measure of the disagreement of the predictions. Evaluation and certification of the ability of a method to detect OOD require specifying instances which are likely to occur in deployment yet on which no prediction is available. Focusing on regression tasks, we choose a simple yet insightful model for this OOD distribution and conduct an empirical evaluation of the ability of various methods to discriminate OOD samples from the data. Moreover, we exhibit evidence that a diversity of parameters may fail to translate to a diversity of predictors. Based on the choice of an OOD distribution, we propose a new way of estimating the entropy of a distribution on predictors based on nearest neighbors in function space. This leads to a variational objective which, combined with the family of distributions given by a generative neural network, systematically produces a diversity of predictors that provides a robust way to detect OOD samples.

翻译：当实例距离训练样本过远时，需要及时检测以防止机器学习模型产生不可信结果，这一挑战被称为分布外（OOD）检测。对于神经网络而言，解决该任务的一种方法是学习一组能够解释训练数据的多样化预测器。该信息可用于通过预测结果的不一致性度量，估计新观测实例的认知不确定性。评估和验证OOD检测方法的能力，需要明确部署中可能出现但尚无预测结果的实例。本研究聚焦回归任务，我们选择了一个简洁而富有洞察力的OOD分布模型，并通过实证评估多种方法区分OOD样本与训练数据的能力。此外，我们证明了参数的多样性可能无法转化为预测器的多样性。基于OOD分布的选择，我们提出了一种新方法——通过在函数空间中寻找最近邻来估计预测器分布的熵。这一方法导出了一个变分目标函数，与生成式神经网络给出的分布族相结合，能够系统性地产生多样化的预测器，从而为OOD样本检测提供稳健方案。