While the choice of prior is one of the most critical parts of the Bayesian inference workflow, recent Bayesian deep learning models have often fallen back on vague priors, such as standard Gaussians. In this review, we highlight the importance of prior choices for Bayesian deep learning and present an overview of different priors that have been proposed for (deep) Gaussian processes, variational autoencoders, and Bayesian neural networks. We also outline different methods of learning priors for these models from data. We hope to motivate practitioners in Bayesian deep learning to think more carefully about the prior specification for their models and to provide them with some inspiration in this regard.
翻译:虽然选择先入为主是贝耶斯人推论工作流程中最关键的部分之一,但最近贝耶斯人的深层次学习模式往往落后于模糊的先入之见,例如标准高斯人。在本审查中,我们强调贝耶斯人的深层学习必须先作出选择,并概述为(深)高斯人进程、变式自动电解器和贝耶斯人神经网络提出的不同前科。我们还概述了这些模型从数据中学习前科的不同方法。我们希望激励巴耶斯人深层学习的从业人员更仔细地思考其模型的先前规格,并在这方面向他们提供一些启发。