论文标题
贝叶斯神经网络中的不确定性校准通过远距离感知先验
Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors
论文作者
论文摘要
随着我们远离数据，预测不确定性应该增加，因为各种各样的解释与鲜为人知的信息一致。我们介绍了远距离感知的先验（DAP）校准，这是一种纠正训练域之外贝叶斯深度学习模型过度自信的方法。我们将DAPS定义为模型参数的先验分布，该模型参数取决于输入，通过衡量其与训练集的距离。 DAP校准对后推理方法不可知，可以作为后处理步骤进行。我们在各种分类和回归问题中证明了其对几个基线的有效性，包括旨在测试远离数据的预测分布质量的基准。
As we move away from the data, the predictive uncertainty should increase, since a great variety of explanations are consistent with the little available information. We introduce Distance-Aware Prior (DAP) calibration, a method to correct overconfidence of Bayesian deep learning models outside of the training domain. We define DAPs as prior distributions over the model parameters that depend on the inputs through a measure of their distance from the training set. DAP calibration is agnostic to the posterior inference method, and it can be performed as a post-processing step. We demonstrate its effectiveness against several baselines in a variety of classification and regression problems, including benchmarks designed to test the quality of predictive distributions away from the data.
