论文标题
功能空间中的广义变异推断：高斯措施符合贝叶斯深度学习
Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning
论文作者
论文摘要
我们开发了一个框架，用于在无限维函数空间中广泛的变异推断，并使用它来构建称为高斯瓦斯林推断（GWI）的方法。 GWI利用了高斯度量之间的Wasserstein距离在正方形函数的Hilbert空间上，以便使用可拖动优化标准确定后部变化，并避免在标准变化功能空间推断中引起的病理。 GWI的令人兴奋的应用是在GWI的变化参数中使用深层神经网络的能力，将其出色的预测性能与类似于高斯过程类似的原则不确定性定量结合在一起。所提出的方法在几个基准数据集上获得了最先进的性能。
We develop a framework for generalized variational inference in infinite-dimensional function spaces and use it to construct a method termed Gaussian Wasserstein inference (GWI). GWI leverages the Wasserstein distance between Gaussian measures on the Hilbert space of square-integrable functions in order to determine a variational posterior using a tractable optimisation criterion and avoids pathologies arising in standard variational function space inference. An exciting application of GWI is the ability to use deep neural networks in the variational parametrisation of GWI, combining their superior predictive performance with the principled uncertainty quantification analogous to that of Gaussian processes. The proposed method obtains state-of-the-art performance on several benchmark datasets.
