论文标题
使用多头辅助网络的不确定性感知（UNA）用于深贝叶斯回归
Uncertainty-Aware (UNA) Bases for Deep Bayesian Regression Using Multi-Headed Auxiliary Networks
论文作者
论文摘要
神经线性模型（NLM）是深贝叶斯模型，通过从数据中学习特征，然后对这些特征进行贝叶斯线性回归产生预测性不确定性。尽管它们很受欢迎，但很少有工作重点是有条不紊地评估这些模型的预测不确定性。在这项工作中，我们证明了NLMS的传统培训程序严重低估了分布外输入的不确定性，因此不能天真地部署在风险敏感的应用程序中。我们确定了这种行为的根本原因，并提出了一个新颖的培训框架，该框架捕获了下游任务的有用的预测不确定性。
Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainties by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have focused on methodically evaluating the predictive uncertainties of these models. In this work, we demonstrate that traditional training procedures for NLMs drastically underestimate uncertainty on out-of-distribution inputs, and that they therefore cannot be naively deployed in risk-sensitive applications. We identify the underlying reasons for this behavior and propose a novel training framework that captures useful predictive uncertainties for downstream tasks.
